code-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing external code.
  • Ingestion points: Code snippets, classes, and methods are ingested via triggers such as /review-code or requests for feedback in SKILL.md.
  • Boundary markers: The skill lacks explicit markers or instructions to delimit user-provided content from the agent's analytical instructions.
  • Capability inventory: The skill is restricted to text generation for feedback; no file-system, network, or command-execution capabilities are present.
  • Sanitization: There is no evidence of input filtering or sanitization to prevent malicious instructions embedded in the code from affecting the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 05:00 PM