The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub and GitLab issue components (titles, bodies, and comments) to generate summaries.
Ingestion points: SKILL.md (Workflow Step 3) specifies reading issue titles, bodies, and comments from external VCS providers.
Boundary markers: The skill lacks specific delimiters or instructions to ignore instructions embedded within the issue content during processing.
Capability inventory: The skill utilizes gh and glab CLI tools for repository cloning, issue commenting, and closing actions.
Sanitization: There is no evidence of sanitization, filtering, or validation of the fetched external issue content.

close-issue