eu-pl-law-tracker
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (scripts/eu_law_identify.py, scripts/eu_law_parse.py, scripts/legal_date_extractor.py, scripts/relation_extractor.py) to parse and identify legal regulations. These scripts are restricted to using Python standard libraries (re, json, argparse, etc.) and do not perform any system-level modifications or network operations.
- [DATA_EXFILTRATION]: No network activity or data transmission patterns were identified. The scripts operate entirely on provided text files and output analysis directly to the console.
- [PROMPT_INJECTION]: The skill provides an indirect prompt injection surface as it is designed to ingest and process external legal documents. Ingestion points: scripts/eu_law_parse.py and scripts/legal_date_extractor.py read content from files specified at runtime. Boundary markers: The scripts do not use explicit delimiters to isolate untrusted content, though the skill instructions emphasize validation against official sources. Capability inventory: The skill uses specialized Python scripts that perform regex-based text extraction; they lack network access, dynamic code execution (eval/exec), or system-modification capabilities. Sanitization: Content is filtered through specific legal pattern matchers (dates, article references, and legal terms) before being returned to the agent context.
- [SAFE]: The skill exhibits high development standards, including the provision of unit tests and clear documentation on source reliability and legal hierarchy. It adheres to the principle of least privilege by not requesting unnecessary tool access.
Audit Metadata