oss-ready
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses local git commands (fetch, pull, stash, rev-parse) to synchronize the repository state and manage feature branches. These operations are restricted to the local environment and the project's configured remote origin.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from existing documentation and package files (Ingestion point: SKILL.md Step 1) to inform the generation of new content. It lacks explicit boundary markers or sanitization for this external data. While the skill can execute git commands and write to the filesystem (Capability inventory: git and file-write access), these actions are limited to standard repository management.
- [SAFE]: Standard community files such as the MIT License, Code of Conduct, and Security Policy are generated from static, local templates within the assets directory, ensuring no reliance on remote code or unverified external downloads.
Audit Metadata