The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to perform both read and write operations on GitHub repositories. Execution includes commands like gh pr list, gh pr view, gh pr checks, gh pr review --approve, and gh pr merge.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from pull request metadata. Ingestion points: PR metadata, including titles and bodies, is ingested from GitHub via gh pr view in SKILL.md. Boundary markers: There are no explicit delimiters or instructions provided to isolate the untrusted PR content from the agent's core instructions. Capability inventory: The skill has write capabilities, including approving pull requests and merging them. Sanitization: No sanitization or filtering is applied to the PR data before it is presented to the agent for analysis.
[EXTERNAL_DOWNLOADS]: Installation instructions reference downloading the skill from the author's GitHub repository (github.com/flc1125/skills), which is a vendor-owned resource.

github-renovate-prs