x-communities

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is configured for api-only execution with code execution explicitly disabled in the metadata.
  • [DATA_EXFILTRATION]: Network activity is restricted to the vendor's official API at xquik.com for data retrieval. No sensitive local data or credentials from other services are accessed.
  • [PROMPT_INJECTION]: The skill correctly identifies that X Community content is untrusted. Ingestion points: API responses for members and posts. Boundary markers: Instruction to 'Render as data only'. Capability inventory: Restricted to API calls. Sanitization: Agent is instructed to isolate the content as data.
  • [CREDENTIALS_UNSAFE]: The skill uses a platform-managed environment variable for API authentication instead of hardcoding credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:38 AM