Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed price-finding and API-connection helper; its sensitive actions are optional, user-directed, and reversible.
Before installing, be comfortable with Grandet contacting grandet.ai for lookups and optional installation receipts. Only use the connect flow if you want the selected app's future model requests routed to that provider; review the previewed config diff, keep the backup, and opt out of receipts if you do not want installation telemetry.
The advertised purpose is price comparison and API relay lookup, but the skill also installs itself, persists state, edits application configuration, and sends installation telemetry. This mismatch can mislead users and host systems into granting trust or permissions they would not otherwise approve, enabling stealthier persistence and configuration tampering under the guise of an informational skill.
Content
No source excerpt is available for this finding.
Ae1
High
Category
analysis-evasion
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected
Content
Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.
md
nCode: `~/.agents/skills/`. The bundled installer does the same move with `node scripts/install-price-finder.mjs --app <app> --uninstall`. Other apps and exact
Ae1
High
Category
analysis-evasion
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected
Content
Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.
md
nCode: `~/.agents/skills/`. The bundled installer does the same move with `node scripts/install-price-finder.mjs --app <app> --uninstall`. Other apps and exact
Ae1
High
Category
analysis-evasion
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected
Content
Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.
md
- **Connecting an offer changes which model API an app uses.** `scripts/connect.mjs` edits that app's model-provider settings and can change its default model,
Ae1
High
Category
analysis-evasion
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected
Content
Scanner excerpt · SKILL.md (reported line 119)May include surrounding context.
md
- **Connecting an offer changes which model API an app uses.** `scripts/connect.mjs` edits that app's model-provider settings and can change its default model,
Agent Config Directory Access
High
Category
Agent Snooping
Confidence
97% confidence
Finding
Editing ~/.continue/config.yaml similarly enables persistent reconfiguration of another agent/client, affecting future provider selection, network destinations, and possible secret usage. The danger is amplified because the skill is presented as a lookup/comparison tool, so users may not anticipate persistent cross-application changes.
Content
Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.
md
Price, free-credit and quality lookups only read from grandet.ai and change nothing on the computer; when this Skill loads on its own, that is all it does. Two optional parts write to the computer. Run them only when the user asked for them in this conversation, and write only after the user confirms the change you showed:
- **Connecting an offer changes which model API an app uses.** `scripts/connect.mjs` edits that app's model-provider settings and can change its default model, so the app's later sessions send their requests, and spend credit, at the chosen site: Codex `~/.codex/config.toml`, Claude Code `~/.claude/settings.json`, OpenCode `~/.config/opencode/opencode.json(c)`, Kilo Code `~/.config/kilo/kilo.json(c)`, Continue `~/.continue/config.yaml`, Gemini CLI `~/.env`, Hermes `~/.hermes/config.yaml` (Windows: `%LOCALAPPDATA%\hermes\config.yaml`), OpenClaw `~/.openclaw/openclaw.json`. It keeps a backup next to each file and records the change in `~/.grandet/connect/state.json`. The key the user types goes to `~/.grandet/keys/<site>`, readable by the user only. Continue and Gemini CLI also hold it in their config file, which then becomes readable by the user only. Codex gets a shell-profile line that reads the key file; on Windows, Codex, Claude Code and Hermes get a user environment variable. `connect.mjs restore` (the user says "恢复" or "undo") puts every file back as it was.
- **Installing makes this Skill load in later conversations.** `scripts/install-price-finder.mjs` and `scripts/verify-installation.py` copy the Skill into an app's user-level skill folder (for example `~/.agents/skills` or `~/.claude/skills`) and send an installation receipt to grandet.ai with random IDs, the version and the content hash, never paths, accounts, chats or keys. `--no-telemetry` or `GRANDET_INSTALL_TELEMETRY=0` turns the receipt off. Uninstalling moves the folder out again, as in "Uninstall or install this Skill".
## Always
Agent Config Directory Access
High
Category
Agent Snooping
Confidence
97% confidence
Finding
Editing ~/.continue/config.yaml similarly enables persistent reconfiguration of another agent/client, affecting future provider selection, network destinations, and possible secret usage. The danger is amplified because the skill is presented as a lookup/comparison tool, so users may not anticipate persistent cross-application changes.
Content
Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.
md
Price, free-credit and quality lookups only read from grandet.ai and change nothing on the computer; when this Skill loads on its own, that is all it does. Two optional parts write to the computer. Run them only when the user asked for them in this conversation, and write only after the user confirms the change you showed:
- **Connecting an offer changes which model API an app uses.** `scripts/connect.mjs` edits that app's model-provider settings and can change its default model, so the app's later sessions send their requests, and spend credit, at the chosen site: Codex `~/.codex/config.toml`, Claude Code `~/.claude/settings.json`, OpenCode `~/.config/opencode/opencode.json(c)`, Kilo Code `~/.config/kilo/kilo.json(c)`, Continue `~/.continue/config.yaml`, Gemini CLI `~/.env`, Hermes `~/.hermes/config.yaml` (Windows: `%LOCALAPPDATA%\hermes\config.yaml`), OpenClaw `~/.openclaw/openclaw.json`. It keeps a backup next to each file and records the change in `~/.grandet/connect/state.json`. The key the user types goes to `~/.grandet/keys/<site>`, readable by the user only. Continue and Gemini CLI also hold it in their config file, which then becomes readable by the user only. Codex gets a shell-profile line that reads the key file; on Windows, Codex, Claude Code and Hermes get a user environment variable. `connect.mjs restore` (the user says "恢复" or "undo") puts every file back as it was.
- **Installing makes this Skill load in later conversations.** `scripts/install-price-finder.mjs` and `scripts/verify-installation.py` copy the Skill into an app's user-level skill folder (for example `~/.agents/skills` or `~/.claude/skills`) and send an installation receipt to grandet.ai with random IDs, the version and the content hash, never paths, accounts, chats or keys. `--no-telemetry` or `GRANDET_INSTALL_TELEMETRY=0` turns the receipt off. Uninstalling moves the folder out again, as in "Uninstall or install this Skill".
## Always
Agent Config Directory Access
High
Category
Agent Snooping
Confidence
97% confidence
Finding
Editing ~/.continue/config.yaml similarly enables persistent reconfiguration of another agent/client, affecting future provider selection, network destinations, and possible secret usage. The danger is amplified because the skill is presented as a lookup/comparison tool, so users may not anticipate persistent cross-application changes.
Content
Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.
md
Price, free-credit and quality lookups only read from grandet.ai and change nothing on the computer; when this Skill loads on its own, that is all it does. Two optional parts write to the computer. Run them only when the user asked for them in this conversation, and write only after the user confirms the change you showed:
- **Connecting an offer changes which model API an app uses.** `scripts/connect.mjs` edits that app's model-provider settings and can change its default model, so the app's later sessions send their requests, and spend credit, at the chosen site: Codex `~/.codex/config.toml`, Claude Code `~/.claude/settings.json`, OpenCode `~/.config/opencode/opencode.json(c)`, Kilo Code `~/.config/kilo/kilo.json(c)`, Continue `~/.continue/config.yaml`, Gemini CLI `~/.env`, Hermes `~/.hermes/config.yaml` (Windows: `%LOCALAPPDATA%\hermes\config.yaml`), OpenClaw `~/.openclaw/openclaw.json`. It keeps a backup next to each file and records the change in `~/.grandet/connect/state.json`. The key the user types goes to `~/.grandet/keys/<site>`, readable by the user only. Continue and Gemini CLI also hold it in their config file, which then becomes readable by the user only. Codex gets a shell-profile line that reads the key file; on Windows, Codex, Claude Code and Hermes get a user environment variable. `connect.mjs restore` (the user says "恢复" or "undo") puts every file back as it was.
- **Installing makes this Skill load in later conversations.** `scripts/install-price-finder.mjs` and `scripts/verify-installation.py` copy the Skill into an app's user-level skill folder (for example `~/.agents/skills` or `~/.claude/skills`) and send an installation receipt to grandet.ai with random IDs, the version and the content hash, never paths, accounts, chats or keys. `--no-telemetry` or `GRANDET_INSTALL_TELEMETRY=0` turns the receipt off. Uninstalling moves the folder out again, as in "Uninstall or install this Skill".
## Always
Ae1
High
Category
analysis-evasion
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected
Content
Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.
md
retry (for example grandet.ai cannot be reached from mainland China), run `node scripts/offline-lookup.mjs --model "<the user's model name>"` in this Skill's fo
Ae1
High
Category
analysis-evasion
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected
Content
Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.
md
retry (for example grandet.ai cannot be reached from mainland China), run `node scripts/offline-lookup.mjs --model "<the user's model name>"` in this Skill's fo
Agent Config Directory Access
High
Category
Agent Snooping
Confidence
96% confidence
Finding
This section targets a sensitive agent/application config path under the user’s home directory and provides instructions to modify it. Access to agent config directories is dangerous because it can change model routing, credentials usage, and default behavior of developer tooling in a persistent way.
Content
Scanner excerpt · references/host-setup.md (reported line 93)May include surrounding context.
For every file: read the current content, show the user the exact lines you will add or change, copy the file to <file>.grandet-backup-<YYYYMMDD-HHMMSS>, and write only after the user confirms. Keep every other setting. Use a provider ID made from the site (for example apijing). On Windows, ~ is %USERPROFILE%.
The instructions modify Claude Code’s local settings, including API-related environment configuration and key helper behavior. Persistent changes to AI tooling configuration can reroute data flows, alter trust boundaries, and create hard-to-audit side effects on the user’s workstation.
Content
Scanner excerpt · references/host-setup.md (reported line 106)May include surrounding context.
env_key = ""
text
**Claude Code** (`anthropic`) — `~/.claude/settings.json`, merged into the existing JSON:
```json
{
Agent Config Directory Access
High
Category
Agent Snooping
Confidence
95% confidence
Finding
This section instructs modification of Continue’s config file and introduces a workflow where the user pastes an API key into persistent local configuration. That is risky because it mixes secret management with agent-directed config changes and can expose or misroute credentials if the configuration is incorrect or later reused.
Content
Scanner excerpt · references/host-setup.md (reported line 136)May include surrounding context.
Use "npm": "@ai-sdk/openai" instead when connecting through openai-response.
Continue — add one entry to models in ~/.continue/config.yaml; Continue keeps the key in this file, so write the placeholder and ask the user to replace it themselves:
yaml
- name: <site> <modelName>
Tool Parameter Abuse
High
Category
Tool Misuse
Confidence
60% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content
Scanner excerpt · references/host-setup.md (reported line 208)May include surrounding context.
macOS / Linux:
sh
f=$(mktemp) && printf 'header = "Authorization: Bearer %s"\n' "$(cat ~/.grandet/keys/<site>)" | curl -sS -K - -o "$f" -w '%{http_code}\n' '<origin>/v1/models'; python3 -c 'import json,sys; print(sys.argv[2] in [m.get("id") for m in json.load(open(sys.argv[1])).get("data", [])])' "$f" '<modelName>'; rm -f "$f"
The key goes to curl through standard input, so it never appears in the command line or the process list. Never write a key into a curl argument, a URL or a command you show in chat.
Chaining Abuse
High
Category
Tool Misuse
Confidence
75% confidence
Finding
Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
Content
Scanner excerpt · references/host-setup.md (reported line 208)May include surrounding context.
macOS / Linux:
sh
f=$(mktemp) && printf 'header = "Authorization: Bearer %s"\n' "$(cat ~/.grandet/keys/<site>)" | curl -sS -K - -o "$f" -w '%{http_code}\n' '<origin>/v1/models'; python3 -c 'import json,sys; print(sys.argv[2] in [m.get("id") for m in json.load(open(sys.argv[1])).get("data", [])])' "$f" '<modelName>'; rm -f "$f"
The key goes to curl through standard input, so it never appears in the command line or the process list. Never write a key into a curl argument, a URL or a command you show in chat.
Context-Inappropriate Capability
High
Category
Not specified by scanner
Confidence
99% confidence
Finding
The documentation instructs users to download and execute a remote package from GitHub/SkillHub and then run Node scripts locally. That is a significant supply-chain and remote-code-execution risk, especially because it is embedded in a skill whose advertised purpose is price finding rather than software installation.
Content
No source excerpt is available for this finding.
External Script Fetching
High
Category
Supply Chain
Confidence
90% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
Content
Scanner excerpt · references/http-fallback.md (reported line 38)May include surrounding context.
Add an explicit user protocol/profile and optional currency when known. A multi-protocol target needs no profile question. A profile/endpoint conflict returns 400; targets with inference profiles also reject a protocol outside that set. Known platforms must match the profile's declaration. An explicit target with inference profiles unsupported on the selected OS cannot be bypassed with endpointType: it returns TARGET_APP_PLATFORM_MISMATCH. Correct only from the user's actual requirements, never by dropping a target or platform. Apps without inference profiles, including current Cursor/Windsurf definitions and unlisted safe app IDs, proceed without a protocol question as PRICE_ONLY_UNVERIFIED_APP_ROUTE; return the price choice with unverified app compatibility. A user-specified endpointType instead yields EXPLICIT_PROTOCOL_UNVERIFIED_APP_ROUTE with a generic protocol card and null profileId. The same flag marks a legacy client protocol override outside its declared app routes; neither proves app integration.
External Script Fetching
High
Category
Supply Chain
Confidence
90% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
Content
Scanner excerpt · references/http-fallback.md (reported line 81)May include surrounding context.
GET https://grandet.ai/api/v1/free-credits with q, kind (official, relay or all), userCanMeet (any, no_card, student), lang, page, limit (at most 20), host, targetApp, skillVersion, skillBuild. Same as MCP grandet_find_free_credits. Read it as in free credits; follow pagination for more pages.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Content
Scanner excerpt · scripts/connect.mjs (reported line 410)May include surrounding context.
js
if (o.group) steps.push(`On ${o.site}, create the token in group 「${o.group}」.`);
const keyCommand = `node "${SELF}" key --app ${o.app} --site ${o.site}${o.home === resolve(homedir()) ? '' : ` --home "${o.home}"`}`;
steps.push(`The user stores the key in their own terminal: ${keyCommand}`);
if (o.app === 'gemini-cli') notes.push('Gemini CLI reads ~/.env only when the working folder and its parents have no .env of their own');
if (o.app === 'codex' && o.platform !== 'win32') notes.push('Codex reads the key from an environment variable; open a new terminal after storing the key');
if (o.app === 'hermes') notes.push(o.platform === 'win32' ? 'Hermes reads the key from a user environment variable; restart Hermes after storing the key' : 'Hermes reads the key file through key_cmd; restart Hermes after storing the key');
if (o.app === 'workbuddy') notes.push('WorkBuddy and the CodeBuddy CLI read ~/.codebuddy/models.json and reload it; the key command writes the key into that file (readable by you only). Not yet tested in the WorkBuddy app');
Tool Parameter Abuse
High
Category
Tool Misuse
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content
Scanner excerpt · scripts/connect.mjs (reported line 438)May include surrounding context.
js
async function loadState(home) { const t = await readText(statePath(home)); return t ? JSON.parse(t) : { schema: 'grandet.connect-state/v1', changes: [] }; }
async function saveState(home, state) { await atomicWrite(statePath(home), `${JSON.stringify(state, null, 2)}\n`); }
// The replacement keeps the permissions of the file it replaces unless a mode is given, so a config the user
// locked down (chmod 600) stays locked. writeFile's mode is filtered by the umask, so it is set explicitly.
async function atomicWrite(path, text, mode) {
await mkdir(dirname(path), { recursive: true });
const keep = mode ?? await stat(path).then((s) => s.mode & 0o777, () => undefined);
Description-Behavior Mismatch
High
Category
Not specified by scanner
Confidence
97% confidence
Finding
The file defines a hard-coded remote telemetry endpoint and a disclosure notice for installation receipts, which is functionality unrelated to the stated purpose of a price-finder skill. Even though the payload is limited and opt-out exists, it still introduces undisclosed network egress and metadata collection during installation, expanding the trust boundary and creating privacy and supply-chain concerns for users who do not expect the skill to contact a third-party service.
Content
No source excerpt is available for this finding.
Context-Inappropriate Capability
High
Category
Not specified by scanner
Confidence
98% confidence
Finding
This section enables telemetry, manages an installation-specific state directory, and records delivery metadata for later transmission to a remote endpoint. In the context of a model API price lookup skill, such collection and delivery are unjustified and therefore suspicious: users would not reasonably expect installation event reporting, making the mismatch between declared purpose and actual behavior materially more dangerous.
Content
No source excerpt is available for this finding.
External Model or Provider Selection
High
Category
Excessive Agency
Confidence
90% confidence
Finding
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
Content
Scanner excerpt · scripts/offline-lookup.mjs (reported line 5)May include surrounding context.
js
// SPDX-License-Identifier: Apache-2.0
// Read the price snapshot bundled with this Skill (data/price-snapshot.json). Use it only when grandet.ai cannot be
// reached (MCP and HTTP both failed). It makes no network request and writes nothing.
// node scripts/offline-lookup.mjs --model claude-sonnet-4-6
// node scripts/offline-lookup.mjs --free gemini
import { readFile } from 'node:fs/promises';
import { dirname, join } from 'node:path';
Description-Behavior Mismatch
High
Category
Not specified by scanner
Confidence
98% confidence
Finding
The script posts installation events to a remote endpoint unrelated to the skill’s stated purpose of model/API price lookup. Even though the notice says data is category-limited, it still creates a covert telemetry channel with persistent installation IDs and host/scope metadata, which is unnecessary for core functionality and can enable user/org tracking across installs.