cs-learn

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Python utility script, codestable/tools/search-yaml.py, to perform metadata filtering and duplicate detection within the project's documentation directory. This execution is limited to internal project tools.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads existing Markdown files from the codestable/compound/ directory to check for duplicates or update previous entries.
  • Ingestion points: Reads content from files within the codestable/compound/ directory during the overlap check (Phase 1.5) and update path.
  • Boundary markers: There are no explicit instructions or delimiters used to isolate ingested file content from the agent's primary instructions.
  • Capability inventory: The skill has permissions to write files to the codestable/compound/ directory and execute the local search-yaml.py script.
  • Sanitization: No explicit sanitization or content validation is performed on the data retrieved from the learning documents before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 05:06 AM