The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard command-line tools (git and gh) to automate local repository management and GitHub interactions. This is consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. * Ingestion points: Processes untrusted data from git status, git diff, git log, and user-provided issue identifiers in SKILL.md. * Boundary markers: No explicit delimiters are used to separate repository data from task instructions. * Capability inventory: Performs subprocess calls to git and gh in SKILL.md. * Sanitization: No explicit sanitization of ingested data is performed before interpolation into the PR body.

beaver-pr