wt-new
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell-level operations using the
gitCLI, specificallygit fetch originandgit worktree add. These commands are assembled dynamically using parameters provided at runtime. - [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (specifically command injection) through the interpolation of untrusted data into shell commands.
- Ingestion points: The
BRANCH_NAMEandBASE_BRANCHparameters defined inSKILL.mdare directly incorporated into shell commands. - Boundary markers: No boundary markers or instructions to ignore embedded instructions are present in the parameter handling logic.
- Capability inventory: The skill executes subprocesses via
gitwhich, if manipulated, can affect the local file system and repository state. - Sanitization: There is no evidence of input validation, escaping, or sanitization for the provided branch names before they are passed to the shell.
Audit Metadata