github
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which creates a surface for indirect prompt injection. 1. Ingestion points: Pull request bodies and issue descriptions as outlined in SKILL.md. 2. Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions embedded within external data. 3. Capability inventory: The skill utilizes the gh CLI for management tasks including creating and merging pull requests. 4. Sanitization: No explicit input sanitization or validation of external text is mentioned.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the gh command-line interface, which involves executing shell-level commands based on repository data and user input.
Audit Metadata