address-pr-comments
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes shell commands using the GitHub CLI (
gh) and the extensiongh pr-reviewto fetch repository data. These are standard interactions with a well-known service.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon content from external, untrusted sources in the form of pull request comments. (1) Ingestion points: Untrusted data enters the agent context through the output ofgh pr-reviewandgh pr viewcommands. (2) Boundary markers: The instructions do not specify delimiters or provide warnings to the agent to treat the fetched comments as raw data rather than instructions. (3) Capability inventory: The agent is empowered to modify the source code ("make the change") and resolve PR conversations based on the content of these comments. (4) Sanitization: The skill provides no mechanisms for sanitizing or validating the comment text before it is processed.
Audit Metadata