welcome
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes external data from GitHub issues and pull requests, such as titles and bodies, which are ingested into the agent context in SKILL.md. To mitigate risks, the skill includes a specific 'Injection guard' and instructions to treat this content as data rather than instructions. Additionally, the skill requires a maintainer's explicit approval before using the GitHub CLI to post any comments, ensuring a human-in-the-loop check.
- Command Execution: The skill relies on the GitHub CLI (gh) to retrieve metadata and interact with repository threads. These commands are integral to the skill's mentoring purpose and are executed within the scope of the user's project configuration.
- Project Setup Validation: A pre-flight check in SKILL.md runs a local Python-based utility to verify the skill's integrity and configuration state. This process ensures the environment is correctly prepared before proceeding with the main logic.
Audit Metadata