issue-to-implementation
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it fetches and analyzes external data from GitHub issues to determine its actions.
- Ingestion points: Issue details and comments are retrieved using the
ghCLI inscripts/fetch_issue.shand parsed inscripts/validate_bug.sh. - Boundary markers: The skill lacks instructions or delimiters to help the agent distinguish between its own system instructions and potentially malicious instructions embedded in the issue content.
- Capability inventory: The agent can execute shell commands, manage git branches, commit code, and create pull requests, providing a significant impact if an injection is successful.
- Sanitization: No sanitization or safety filtering is performed on the data fetched from GitHub before it is analyzed by the agent.- [COMMAND_EXECUTION]: The skill performs various automated repository operations using command-line tools.
- Evidence: It uses
gitfor branch and commit management,ghfor GitHub API interactions, andbunorbunxfor executing local tests and development tools.
Audit Metadata