The Agent Skills Directory

[COMMAND_EXECUTION]: Employs the official GitHub CLI (gh) to perform repository operations such as triaging issues, managing pull requests, and creating releases.
[DATA_EXFILTRATION]: Accesses repository metadata and security alert statuses (Dependabot and secret scanning), which is consistent with the skill's stated purpose of security monitoring and maintenance.
[PROMPT_INJECTION]: Processes external, untrusted data from GitHub issue titles, bodies, and pull request comments, which presents a surface for indirect prompt injection.
Ingestion points: Fetches content via gh issue list, gh pr view, gh run view, and gh api calls.
Boundary markers: No specific delimiters are instructed for use when the agent processes the retrieved issue or PR content.
Capability inventory: Includes write-access tools such as gh issue edit, gh issue comment, and gh release create.
Sanitization: The instructions do not define methods for sanitizing or validating ingested external content.

github-ops