cohesion-coupling-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze user-provided code changes, which presents a surface for indirect prompt injection attacks.
  • Ingestion points: User-provided source code files and pull request descriptions.
  • Boundary markers: Absent; there are no specific delimiters or instructions for the AI to ignore instructions embedded within the code being reviewed.
  • Capability inventory: The skill itself is purely instructional and does not define subprocess calls or file-writing tools, though it references a local script (scripts/dependency-cruiser.js).
  • Sanitization: No evidence of input validation or escaping of the code being processed.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): No remote scripts are downloaded or executed. References to external files are limited to local repository paths.
  • [Data Exposure & Exfiltration] (SAFE): No evidence of credential harvesting, access to sensitive environment files, or exfiltration to non-whitelisted domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM