The Agent Skills Directory

[PROMPT_INJECTION]: The skill fetches content from external GitHub issues (titles, bodies, and comments) which could theoretically contain malicious instructions designed to influence the agent's behavior. \n- Ingestion points: Fetches issue data via gh issue view in SKILL.md. \n- Boundary markers: No specific delimiters or instructions are used to separate fetched issue content from the agent's core instructions. \n- Capability inventory: The agent has permissions to read local files (e.g., package.json, CLAUDE.md) and execute gh commands. \n- Sanitization: There is no evidence of sanitization or filtering of the external issue data before processing.
[SAFE]: The skill utilizes the official GitHub CLI (gh), a trusted and well-known service, and only accesses standard project metadata files.

analyze-issue