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