x-trends

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it ingests and processes untrusted user-generated content from X.
  • Ingestion points: Untrusted data enters the agent context via the 'name' and 'context' fields returned by the trending topics API endpoint.
  • Boundary markers: The skill includes explicit defensive instructions stating that trend names and contexts should be rendered as data only and never treated as instructions.
  • Capability inventory: The skill is restricted to 'api-only' execution with no capabilities for file system modification or code execution.
  • Sanitization: The skill does not perform programmatic filtering or sanitization of the fetched strings, relying instead on model instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:38 AM