Back to skill

Security audit

stock-terminal

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this skill as benign with medium confidence: most checks are OK, while concerns are limited by incomplete inspection and notes about its declared scope and command wording.

The verdict is benign, but it does not mean risk-free. Before installing, consider that some files were not fully inspected and that network capability is detected without a declared tool scope; scanner evidence about runtime permissions is unavailable.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

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 416)May include surrounding context.

md
For routing, cache identity, and exact call chains, read [commands and data](references/commands-and-data.md).

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 418)May include surrounding context.

md
For XML authoring and typed repair errors, read [canvas grammar](references/canvas-grammar.md).

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 420)May include surrounding context.

md
For deterministic replays and the separate fresh-build exercise, read [verification](references/verification.md).

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

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.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/commands-and-data.md (reported line 22)May include surrounding context.

md
the response supplies one, separate from the host fetch time. Also retain preview and error state.
Coalesce identical in-flight requests so a tool and a widget do not pay for the same snapshot twice.
Snapshot inputs include bound selector values, including fixed query inputs such as the chart's
`timeframe: "1M"`. They are not limited to arguments typed by the user; the binding validator needs
the actual ticker and period that produced the data.

Before binding a default relative window, use [request-cache.mjs](runtime/request-cache.mjs).

Unqualified everyday phrases are exposed as financial-skill commands without explicit invocation boundaries.

Low
Category
Trigger Abuse
Confidence
91% confidence
Finding

The standalone command "mood" can refer to a user's emotional state rather than market sentiment. Similarly, "what's hot today?" (L1626) and "stories" (L1948) overlap with ordinary nonfinancial requests, and the manifest does not require an explicit financial context or skill-command mode.

Content

No source excerpt is available for this finding.