canonical-project-skills-layout
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate project maintenance tasks. It includes a bash script that automates the migration of agent configuration files (CLAUDE.md/AGENTS.md) and skill directories to a standardized layout.
- [COMMAND_EXECUTION]: The skill executes a local bash script to perform file system operations (mkdir, ln, mv, rm) and git operations. These actions are transparently documented and include safety checks, such as refusing to proceed if there are uncommitted changes or content conflicts.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes file names and specific file contents (checking for the @AGENTS.md import string), it does not execute instructions contained within the processed data. The attack surface is minimal and handled via standard shell utilities (ls, awk, sed) for structural verification only.
Audit Metadata