Back to skill

Security audit

自选清单增量日报

Security checks for vulnerabilities and agentic risk

Overview

The reporting workflow is coherent, but its optional connection setup has flaws that could expose your API key to an unapproved destination.

Use the offline, user-supplied-data path until credential handling is fixed. Before supplying an API key, require HTTPS and approved-host checks in the shell examples and redirect protection in the helper. Review and pin optional installations. Cue queries reveal selected companies; live services and separately installed skills were not evaluated.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
Findings (28)

Tainted flow: 'req' from os.environ.get (line 188, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/cue_connectivity_check.py (reported line 193)May include surrounding context.

python
code = None
    raw = ""
    try:
        with urllib.request.urlopen(req, timeout=args.timeout) as resp:
            code, raw = resp.status, resp.read().decode("utf-8", "replace")
    except urllib.error.HTTPError as err:
        detail = ""

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 · README.en.md (reported line 96)May include surrounding context.

bash
   CATALOG="https://cuecue.cn/api/mcp-catalog"
   curl -s "$CATALOG" | python3 -c 'import json,sys
   rows=json.load(sys.stdin)["data"]["domains"]
   [print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
   DOMAIN_ID="<replace with one of the ids listed by the line above>"

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 · README.en.md (reported line 100)May include surrounding context.

md
rows=json.load(sys.stdin)["data"]["domains"]
   [print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
   DOMAIN_ID="<replace with one of the ids listed by the line above>"
   ROUTING_URL="$(curl -s "$CATALOG" | python3 -c 'import json,sys
   rows=json.load(sys.stdin)["data"]["domains"]
   hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
   print(*hit,sep="\n") if hit else sys.exit("Not found: that id is not in the catalog response (or its routing has no url field) - run the line above and pick one of the ids listed")' "$DOMAIN_ID")"

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 · README.md (reported line 97)May include surrounding context.

bash
   CATALOG="https://cuecue.cn/api/mcp-catalog"
   curl -s "$CATALOG" | python3 -c 'import json,sys
   rows=json.load(sys.stdin)["data"]["domains"]
   [print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
   DOMAIN_ID="<把这里换成上一行列出的那个域 id>"

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 · README.md (reported line 101)May include surrounding context.

md
rows=json.load(sys.stdin)["data"]["domains"]
   [print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
   DOMAIN_ID="<把这里换成上一行列出的那个域 id>"
   ROUTING_URL="$(curl -s "$CATALOG" | python3 -c 'import json,sys
   rows=json.load(sys.stdin)["data"]["domains"]
   hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
   print(*hit,sep="\n") if hit else sys.exit("未取到:该 id 不在目录现值里(或它没有 routing 里的 url 字段)——先跑上面那行列出现场的 id 再填")' "$DOMAIN_ID")"

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk has a materially different operational purpose: testing service connectivity. Catalog lookup and authentication could support a larger reporting skill, but this standalone diagnostic does not implement or invoke the advertised watchlist workflow. Its credential-bearing request is explicit and destination-guarded, so the code does not establish malicious exfiltration. The mismatch is between the declared daily-reporting purpose and the diagnostic behavior actually shown; other, unsupplied files might implement the reporting workflow.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

md
通道怎么开:三层(注册 → 取 api-key → 装 skill 后还要实连才算连上)写在 `README.md` §三 末小节,那一格给一条可执行的安装命令(本件 `npx skills add huhoo/cue-awesome --skill watchlist-digest-cn`;取证腿整套与单装两种写法)

Automatic redirects bypass the documented HTTPS and authorized-host guarantees for credential transmission.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The destination guard checks only the initial URL, while urllib's default redirect handler can follow a POST's 301, 302, or 303 response as a GET and copy the Authorization header to the redirected request. An authorized endpoint that is compromised or exposes an attacker-controlled redirect could therefore leak CUE_API_KEY to an unauthorized host or an HTTP destination, contradicting the documented credential-transmission guarantees.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The installation command executes an unpinned npm CLI and installs skill content from a mutable repository reference. Although this is not specifically an MCP-server declaration, a compromised future release or repository update could execute code or introduce adversarial agent instructions.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.en.md (reported line 43)May include surrounding context.

bash
# 1. Put it in the skills directory (either route; afterwards list installed skills again and seeing watchlist-digest-cn there is what proves the files landed)
npx skills add huhoo/cue-awesome --skill watchlist-digest-cn
mkdir -p ~/.workbuddy/skills
cp -r watchlist-digest-cn ~/.workbuddy/skills/

# 2. Settle the list -> run the increment -> pass the gate (section 1)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 43)May include surrounding context.

bash
# 1. 放到技能目录(两条路任选,装完重列一次已安装 skill 看得到 watchlist-digest-cn 才算文件到位)
npx skills add huhoo/cue-awesome --skill watchlist-digest-cn
mkdir -p ~/.workbuddy/skills
cp -r watchlist-digest-cn ~/.workbuddy/skills/

# 2. 落清单 → 跑增量 → 过机检(三步见 §一)

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The collection installation command leaves both the executable npm CLI and the source collection unpinned. Selecting individual skills does not establish their integrity, so upstream compromise could introduce malicious code or agent instructions.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

Naming a particular skill does not pin its content or the npm CLI that installs it. A mutable upstream release could therefore run unexpected code or install altered instructions into an agent environment that uses credentials.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This paragraph repeats the unpinned installation command; checking that a skill appears in the installed list establishes presence, not integrity. It repeats the same supply-chain exposure as the earlier installation example rather than introducing a distinct attack mechanism.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The shell example attaches the API key to a URL taken directly from the catalog without validating its scheme or authorized host. A compromised catalog response could direct the credential to an attacker-controlled or plaintext endpoint; the separately described script's destination checks do not protect this curl example.

Content

Scanner excerpt · README.en.md (reported line 105)May include surrounding context.

md
hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
   print(*hit,sep="\n") if hit else sys.exit("Not found: that id is not in the catalog response (or its routing has no url field) - run the line above and pick one of the ids listed")' "$DOMAIN_ID")"
   [ -n "$ROUTING_URL" ] || { echo "Fetch failed: ROUTING_URL is empty - run the line above, then set DOMAIN_ID to one of the ids listed" >&2; exit 1; }
   curl -s -X POST "$ROUTING_URL" \
     -H "Authorization: Bearer $CUE_API_KEY" \
     -H "Accept: application/json, text/event-stream" \
     -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The command executes an unpinned npm CLI and installs skill content without an immutable repository revision. Despite the finding's inaccurate MCP-server label, the command creates supply-chain exposure to malicious upstream code or agent instructions.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The whole-collection installation uses mutable references for both the npm CLI and the skill collection. Interactive selection limits what is installed but does not prevent compromised upstream content from reaching the agent environment.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The single-skill command identifies a skill by name but pins neither its content nor the installer. An upstream compromise could therefore introduce code execution or malicious instructions, with additional relevance because these evidence skills are used around an API credential.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The installation-status paragraph repeats an unpinned installation command, so following it retains the same upstream supply-chain risk. Finding a skill name in the installed list does not verify the integrity of its executable files or instructions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The curl command sends the API key to a catalog-provided URL after checking only that it is nonempty. A malicious or compromised catalog entry could select an unauthorized host or plaintext HTTP endpoint, and the safeguards described for the separate Python helper are absent from this shell path.

Content

Scanner excerpt · README.md (reported line 106)May include surrounding context.

md
hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
   print(*hit,sep="\n") if hit else sys.exit("未取到:该 id 不在目录现值里(或它没有 routing 里的 url 字段)——先跑上面那行列出现场的 id 再填")' "$DOMAIN_ID")"
   [ -n "$ROUTING_URL" ] || { echo "取值失败:ROUTING_URL 为空——先跑上面那行列出现场 id,再把 DOMAIN_ID 换成其中之一" >&2; exit 1; }
   curl -s -X POST "$ROUTING_URL" \
     -H "Authorization: Bearer $CUE_API_KEY" \
     -H "Accept: application/json, text/event-stream" \
     -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The external data-fetching workflow lacks a privacy warning that watchlist company identifiers are sent to a third-party service.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow directs the agent to resolve company identifiers and query external data services without clearly disclosing that the user's watchlist identifiers leave the local environment. Although company codes are public, their association with a particular user and repeated queries can reveal investment interests or strategy.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The active onboarding instructions recommend an unpinned npx installation command, allowing the installer package and repository content to change independently of the reviewed skill. A compromised upstream release could execute installer code or install malicious agent instructions; this is a supply-chain issue rather than an MCP server-version issue.

Content

No source excerpt is available for this finding.