tweet-style

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Skill connects to the vendor's API at https://xquik.com/api/v1 to retrieve account style analysis.
  • [PROMPT_INJECTION]: The skill processes untrusted tweet data, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Style data is ingested from external X (Twitter) profiles via API calls to the vendor's backend.
  • Boundary markers: The documentation explicitly warns the agent that profiles are derived from untrusted text and signature phrases should not be treated as instructions.
  • Capability inventory: The skill performs read-only API requests and data summarization; it does not have file-writing or command execution capabilities.
  • Sanitization: No automated sanitization or filtering of the retrieved tweet content is specified in the instruction flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:38 AM