receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process code review feedback from external sources, which represents an entry point for untrusted data into the agent's context.
- Ingestion points: Instructions in
SKILL.mdfor handling 'External Reviewers' feedback. - Boundary markers: There are no explicit delimiters or instructions provided to isolate the feedback content from the agent's internal logic.
- Capability inventory: The agent is empowered to perform filesystem writes and execute GitHub CLI commands (
gh api) based on the feedback. - Sanitization: The instructions do not define sanitization, validation, or escaping procedures for the content of the review feedback prior to its implementation.
- [COMMAND_EXECUTION]: The skill directs the agent to interact with the GitHub API through command-line tools.
- Evidence: Use of
gh api repos/{owner}/{repo}/pulls/{pr}/comments/{comment_id}/repliesdescribed inSKILL.mdfor responding to feedback threads.
Audit Metadata