The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use git and gh (GitHub CLI) for repository operations, including reading state and performing mutations like git rebase, git push, and git reset. These operations are consistent with the skill's stated purpose of assisting with team workflows.
[DATA_EXPOSURE]: The skill utilizes the GitHub CLI to inspect PR metadata and branch information. No data exfiltration to external or unauthorized domains was observed; operations are restricted to the local repository and the connected GitHub remote.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests untrusted data from GitHub.
Ingestion points: Pull request titles, metadata, and commit messages are retrieved via gh pr view and gh api in SKILL.md and reference.md.
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the retrieved GitHub data.
Capability inventory: The agent has the capability to modify repository state using git push, git rebase, and git reset --hard as described in reference.md.
Sanitization: Absent; the skill does not define filters or validation for the data ingested from remote repository resources.

git-workflow-ps-tech