gastown-rig-setup
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill instructs the agent to execute shell commands (git clone, gt rig add, dolt) using unvalidated user inputs for repository URLs and rig names, which could lead to command injection if malicious strings are provided.
- [EXTERNAL_DOWNLOADS] (LOW): The skill facilitates downloading code from external Git repositories via git clone. While necessary for the skill's function, this introduces untrusted third-party code into the local environment.
- [Indirect Prompt Injection] (LOW): The skill ingests data from external repositories and template rigs without sanitization. * Ingestion points: git clone <SSH_URL> and template rig file copies. * Boundary markers: None. * Capability inventory: File-write (git commit), shell execution (gt, bd, dolt), and network operations (git push, dolt push). * Sanitization: None.
Audit Metadata