pr-ready
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git,gh, andglabcommands to perform its primary tasks. These tools are used for repository management and interacting with pull requests and merge requests on GitHub and GitLab. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it fetches and acts upon external data from pull request comments and review bodies.
- Ingestion points: Untrusted data enters the agent context when fetching comments and reviews via
gh apiandglab(documented in SKILL.md under 'Review threads' and 'Forge cheatsheet'). - Boundary markers: The instructions lack delimiters or specific directives to the agent to treat fetched comment text as data rather than instructions.
- Capability inventory: The agent possesses capabilities to execute shell commands (git operations) and perform forge API writes (resolving threads, pushing code), which could be abused if malicious instructions in comments are followed.
- Sanitization: No sanitization, validation, or escaping of the external comment content is specified before interpolation into the agent's workflow.
Audit Metadata