privacy-notice-generator

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts, privacy_notice_scaffolder.py and notice_compliance_checker.py, to generate templates and validate privacy notice text. These scripts rely on standard Python libraries and do not perform network operations or sensitive system modifications.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because the notice_compliance_checker.py script ingests and processes untrusted data from external files. Maliciously crafted privacy notices could contain instructions intended to mislead the agent when it reviews the script's output.\n
  • Ingestion points: scripts/notice_compliance_checker.py (reads content from the file path provided in notice_file).\n
  • Boundary markers: Absent; the script analyzes the full content of the provided file.\n
  • Capability inventory: The agent can execute local scripts and read files. The scripts themselves are limited to string processing and regex validation.\n
  • Sanitization: Absent; input text is processed directly using regular expressions without validation or escaping of potential prompt injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 08:15 AM