prune
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill handles branch names and PR metadata which presents an indirect prompt injection surface.
- Ingestion points: Data is retrieved from
git branchandgh pr listinSKILL.md. - Boundary markers: No explicit markers are used to separate untrusted data from instructions.
- Capability inventory: The skill executes shell commands via Git and uses the
AskUserQuestiontool for confirmation. - Sanitization: Branch names are used directly in shell commands without sanitization.
- [COMMAND_EXECUTION]: The skill executes
gitandghcommands to manage and delete branches. These actions are primary to the skill's purpose and require user approval.
Audit Metadata