The Agent Skills Directory

[SAFE]: The skill is a standard workspace management utility. Analysis of the scripts and instructions reveals no malicious intent, hidden code, or dangerous operations.- [INDIRECT_PROMPT_INJECTION]: The skill reads data from local files (WORKSPACE.md) which could theoretically contain malicious instructions. * Ingestion points: The scripts/affected.py script reads the WORKSPACE.md file from the local directory. * Boundary markers: Absent. * Capability inventory: The skill's capabilities are limited to reading local files and printing to stdout; it lacks network access, privilege escalation, or dynamic execution features. * Sanitization: The script uses a strict regular expression to parse relationship lines, which prevents unstructured text from being processed as logic.

workspace-affected