going-viral

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill communicates with vendor-owned API endpoints at xquik.com to process user topics and handle information as part of its core functionality.
  • [PROMPT_INJECTION]: The workflow involves ingesting untrusted content from social media platforms which presents an indirect prompt injection surface.
  • Ingestion points: GET /x/tweets/search in SKILL.md.
  • Boundary markers: None described.
  • Capability inventory: Limited to API interactions; metadata specifies codeExecution: none.
  • Sanitization: Not explicitly mentioned in the workflow description.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:41 AM