code-review

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a trailing 'ignore this line' string in the SKILL.md file. While likely a placeholder, it follows the pattern of an instruction override attempt.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted code as input without implementing isolation measures.
  • Ingestion points: The skill uses 'Read', 'Grep', and 'Glob' tools to ingest files from the codebase (documented in SKILL.md).
  • Boundary markers: There are no delimiters or specific instructions to the agent to treat reviewed code as data rather than instructions.
  • Capability inventory: The agent has access to file reading tools and 'WebSearch' as defined in the YAML frontmatter.
  • Sanitization: No input validation or sanitization is performed on the reviewed code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:38 PM