x-twitter-research

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates communication with twitr.sh for triggering data exports and polling for status updates. This is the primary function of the skill and uses the vendor's official domain.
  • [PROMPT_INJECTION]: The skill processes external data from X (Twitter), which constitutes an indirect prompt injection surface.
  • Ingestion points: Bulk datasets downloaded via URLs provided by the x_extract API, as noted in SKILL.md.
  • Boundary markers: None explicitly defined in the instructions for handling the downloaded content.
  • Capability inventory: The skill performs network operations via HTTP POST and GET requests to manage extractions.
  • Sanitization: No specific sanitization or filtering steps are prescribed for the agent when summarizing or presenting the downloaded Twitter data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 05:19 PM
Security Audit — agent-trust-hub — x-twitter-research