orchestrate-code-review

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from codebases and diffs.\n
  • Ingestion points: Reads diffs and codebase paths from user-provided inputs as defined in SKILL.md.\n
  • Boundary markers: Lacks explicit boundary markers or instructions to the agent to disregard commands embedded within the reviewed code.\n
  • Capability inventory: Orchestrates a sequence of analytical sub-skills (review-*) and aggregates findings into a final report.\n
  • Sanitization: No sanitization or content validation is performed on the ingested code before it is passed to the sub-skills.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 11:15 AM