The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git and GitHub CLI (gh) commands for repository analysis and branch management. This includes potentially destructive operations such as git branch -D and git push origin --delete. However, these are the core purpose of the skill and are protected by extensive safety logic.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local environment and GitHub API.
Ingestion points: Branch names and metadata from git for-each-ref, and pull request details (state, URLs) from gh pr list in SKILL.md (Steps 2 and 3).
Boundary markers: Absent. The skill does not explicitly define delimiters for external data interpolated into its logic or terminal commands.
Capability inventory: The skill has the capability to delete local and remote branches using the Bash tool (Step 6).
Sanitization: Absent. There is no explicit instruction to sanitize or escape branch names or PR metadata before use in shell commands.
Mitigation: The skill mitigates this risk through a mandatory human-in-the-loop confirmation step (Step 6) and a comprehensive bucketing system that blocks deletion for suspicious or protected states.

git-branch-cleanup