receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external feedback from reviewers, which introduces a surface area for indirect prompt injection attacks.
- Ingestion points: The skill explicitly handles and implements feedback from "External Reviewers" (SKILL.md).
- Capability inventory: The agent is instructed to use
grepto verify code usage andgh apito reply to pull request comment threads (SKILL.md). - Boundary markers: The instructions lack explicit directives to use delimiters or ignore instructions embedded within the processed feedback.
- Sanitization: There are no specific instructions to sanitize or escape the content of external feedback before the agent interpolates it into its processing flow.
- [COMMAND_EXECUTION]: The skill directs the agent to execute specific shell and API commands to fulfill its purpose.
- Evidence: The instructions explicitly mention using
grepto check for code usage (YAGNI check) andgh apifor responding to GitHub reviews.
Audit Metadata