The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute git, gh (GitHub CLI), glab (GitLab CLI), and p4 (Perforce) commands. These commands are used to push code changes, trigger external reviews, and resolve discussion threads in the user's repository environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from pull request comments, merge request notes, and Perforce changelist descriptions, which creates an attack surface for indirect prompt injection.\n
Ingestion points: Data is ingested through gh api (comments and reviews), glab api (notes and discussions), and p4 describe (changelist descriptions) as specified in SKILL.md.\n
Boundary markers: There are no explicit boundary markers or instructions telling the agent to treat fetched comment content as untrusted data or to ignore embedded commands.\n
Capability inventory: The skill has the capability to write to the file system, commit changes, push to remote repositories (git push, p4 shelve), and interact with the platform APIs via the gh, glab, and p4 tools.\n
Sanitization: The instructions do not specify any sanitization, filtering, or validation of the fetched comment text before the agent interprets it to 'fix actionable comments'.

greploop