qrspi-worktree
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands including
git worktree addandcp -rto manage local repository state and files. These operations are triggered based on user-provided paths.- [INDIRECT_PROMPT_INJECTION]: The skill derives branch names and directory paths from user-provided input and interpolates them directly into shell commands, creating a potential command injection surface. - Ingestion points: Artifact directory path provided by the user in SKILL.md.
- Boundary markers: None specified for the user input; it is treated as a trusted variable.
- Capability inventory: Shell execution of
gitandcputilities in SKILL.md. - Sanitization: No validation, escaping, or filtering of the user-provided path is mentioned before it is used in command strings.
Audit Metadata