resolve-pr-comments
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through GitHub PR review comments fetched in
SKILL.mdvia thegh api graphqlquery. - Boundary markers: No explicit delimiters (like XML tags or triple quotes) or 'ignore embedded instructions' warnings are used when the agent processes the fetched comment bodies.
- Capability inventory: The agent uses an 'Edit tool' to modify the codebase and executes
gh apicommands to post comments and resolve threads on GitHub. - Sanitization: The skill lacks validation or sanitization of the comment content, relying on the agent to manually determine if a suggestion 'makes sense' before acting.
- [COMMAND_EXECUTION]: The skill executes several
gh apicommands to query the GitHub GraphQL API and post updates to pull request threads.
Audit Metadata