worktree
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
gitandgh(GitHub CLI) tools to create, remove, and list worktrees. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository environment, such as branch names and pull request identifiers, which are interpolated into shell commands.
- Ingestion points: Branch names (
<branch-name>) and PR identifiers (<n>) in SKILL.md. - Boundary markers: Absent; the skill does not use delimiters to wrap external inputs used in commands.
- Capability inventory: Shell command execution via
gitandghCLIs. - Sanitization: Absent; the skill does not explicitly sanitize or escape branch names or PR identifiers before interpolation into the shell commands.
Audit Metadata