The Agent Skills Directory

[SAFE]: The skill utilizes the official GitHub CLI tool (gh) to perform repository management tasks. All operations, including viewing pull request metadata, checking CI status, and merging branches, are standard developer workflows targeted at a specific monorepo environment.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it ingests untrusted data from external sources.
Ingestion points: Data is ingested from GitHub via gh pr view (PR metadata) and gh run view --log-failed (CI logs) in SKILL.md.
Boundary markers: None present; the instructions do not specify delimiters for external content.
Capability inventory: The skill has the capability to execute merges (gh pr merge) and push code changes (via the referenced pr-ready workflow) as seen in SKILL.md.
Sanitization: None present; the agent is instructed to inspect logs and metadata directly.
Assessment: While an ingestion surface exists, the operations are standard for CI/CD management and the risk is considered negligible within the context of the intended primary purpose of the skill.

merge