Back to skill

Security audit

Signal Skills: review-scout

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence because scanners report private analytics access beyond its review-analysis purpose; some findings remain unconfirmed and scan coverage is partial.

Consider whether the skill needs access to private analytics for your task and whether you can verify and authorize the backend, project, and data being queried. The scanner run is partial: two referenced paths were unresolved, so the evidence does not establish all behavior.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The supplied command retrieves podcast-skill analytics configuration rather than collecting or analyzing product reviews. No connection to the declared review-analysis workflow is shown. The script's implementation is not supplied, so additional behavior or side effects cannot be established.

Content

No source excerpt is available for this finding.

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

The review-mining skill silently selects authenticated internal analytics backends and queries private product telemetry, exceeding its stated review/feedback-mining scope.

Medium
Category
Excessive Agency
Confidence
92% confidence
Finding

The procedure treats a remembered backend or available credentials as sufficient authorization to silently query private telemetry, without confirming the intended project or permission for this task. Although analytics cross-checking is documented as optional and queries are limited, following this procedure automatically could expose unrelated internal metrics in a review report; reading the podcast skill's preference also risks selecting an unintended backend.

Content

No source excerpt is available for this finding.

Tainted flow: 'output' from sys.stdin.read (line 426, user input) → pathlib.Path.write_text (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · render_report.py (reported line 431)May include surrounding context.

python
print(f"payload error: {e}", file=sys.stderr)
            sys.exit(1)

        dst.write_text(output)
        print(f"wrote {dst} ({len(output)} bytes, {len(payload['tiers'])} tiers)")

        if should_open and not opened and dst.suffix.lower() not in TEXT_EXTENSIONS: