The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub Pull Requests, including titles, bodies, comments, and diffs, which act as untrusted ingestion points.
Ingestion points: Content is retrieved using gh pr view and gh pr diff commands as defined in SKILL.md.
Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore potential instructions embedded within the ingested PR data.
Capability inventory: The skill has the capability to write to the repository using gh issue create and gh pr comment in SKILL.md.
Sanitization: No specific sanitization, filtering, or escaping of the fetched PR content is described before it is included in the tracking issue template.

pr-track-v1