The Agent Skills Directory

[SAFE]: A detailed audit of the skill instructions and Python scripts reveals no malicious patterns. The code relies solely on standard libraries for static analysis and documentation rendering.
[COMMAND_EXECUTION]: The skill executes local Python scripts provided within the package. These scripts (tour_propose.py, tour_render.py, tour_validate.py) are used for analytical tasks like AST parsing and note auditing. No untrusted input is passed to shell sinks, and no external code is downloaded.
[DATA_EXFILTRATION]: No network-capable code or exfiltration patterns were found. File access is limited to reading the target repository's source code for documentation purposes, and the results remain within the local execution environment.

code-tour