triage
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted data from GitHub issues and pull requests, creating a surface for malicious content to influence the agent. \n
- Ingestion points: The skill reads issue/PR bodies, comments, author information, and code diffs in
SKILL.md. \n - Boundary markers: No delimiters or protective instructions are defined to separate untrusted user input from the skill's logic. \n
- Capability inventory: The skill can execute shell commands for bug reproduction and uses a script to modify GitHub labels and repository states. \n
- Sanitization: No sanitization or filtering of external content is performed before interpolation into agent prompts. \n- [COMMAND_EXECUTION]: The skill executes the
node ready.mjscommand to transition issues to readiness states. \n- [DYNAMIC_EXECUTION]: Theready.mjsscript performs dynamic operations such as querying the GitHub GraphQL API and importing platform-specific utilities from relative paths.
Audit Metadata