receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages the surface area for indirect prompt injection by defining a process for handling untrusted code review feedback.
- Ingestion points: External reviewer comments and feedback received during the development process are primary sources of untrusted input.
- Boundary markers: The skill lacks technical delimiters but establishes a workflow-based boundary through mandatory verification and evaluation steps (Read, Understand, Verify, Evaluate).
- Capability inventory: The skill references usage of
grepfor code search and the GitHub CLI (gh api) for pull request interactions. - Sanitization: The skill itself functions as a manual verification layer, instructing the agent to prioritize codebase reality and technical reasoning over external suggestions.
Audit Metadata