gsd-new-workspace
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data which could lead to indirect prompt injection if malicious instructions are embedded in the arguments.
- Ingestion points: Untrusted data enters via
{{GSD_ARGS}}(captured after the skill invocation command inSKILL.md). - Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the provided skill definition.
- Capability inventory: The skill performs file system operations (creating directories in
~/gsd-workspaces/), git operations (worktree,clone), and uses thespawn_agenttool to delegate tasks. - Sanitization: No input sanitization or validation logic is defined to protect against malicious arguments or injected instructions.
- [COMMAND_EXECUTION]: The skill initiates system-level operations including git repository cloning and directory management based on parameters (like
--nameand--path) provided by the user.
Audit Metadata