receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core function is to process feedback from external reviewers and implement technical changes based on that input.
- Ingestion points: Code review comments from "External Reviewers" and GitHub pull request threads (SKILL.md).
- Boundary markers: The skill lacks explicit instructions for using delimiters or boundary markers when processing this external input, though it does instruct the agent to "be skeptical" and "check carefully".
- Capability inventory: The agent is expected to read files (via grep), modify code (via "implementation" instructions), and interact with the GitHub API (gh api).
- Sanitization: No specific sanitization or validation of the input content is described.
- [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands to search the codebase and interact with external APIs.
- Evidence: The skill mentions using "grep codebase" to verify usage and "gh api" to post replies to specific GitHub comment threads.
Audit Metadata