privacy-policy-data-map-check-cn

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Python script (scripts/run.py) designed to interface with the AI Skills API to perform analysis tasks.
  • [DATA_EXFILTRATION]: The skill transmits user-provided content, including privacy policy text, uploaded files (data maps, SDK lists), and external URLs, to the vendor's API at https://ai-skills.ai for analysis.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from multiple sources, creating a surface for indirect prompt injection attacks.
  • Ingestion points: The skill accepts data through the privacyPolicyText field, dataMapFile (binary uploads), and privacyNoticeLink (remote URIs).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the skill configuration to isolate user-provided data from system instructions.
  • Capability inventory: The skill uses a Python runner (scripts/run.py) to execute network requests to the remote API service.
  • Sanitization: No local sanitization or validation of input text is performed before transmission to the remote API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:58 AM
Security Audit — agent-trust-hub — privacy-policy-data-map-check-cn