receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and act upon code review feedback from external reviewers, creating an attack surface for indirect prompt injection where malicious instructions could be embedded in the feedback content.
- Ingestion points: External review feedback received via GitHub or other platforms as described in the 'Source-Specific Handling' section of SKILL.md.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the feedback text.
- Capability inventory: Use of
grepfor codebase analysis,gh apifor GitHub interactions, and the general capability to modify files and implement code changes. - Sanitization: Absent. There is no explicit requirement for the agent to sanitize or filter out instructional content from the review feedback before processing.
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools for its operations.
- Evidence: Employs
grepto check for code usage (YAGNI check) andgh apito post replies to GitHub pull request comments.
Audit Metadata