x-api

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion and processing of untrusted data from the X platform.
  • Ingestion points: Content is retrieved from api.x.com endpoints for searching tweets and user timelines as documented in SKILL.md.
  • Boundary markers: The skill does not define delimiters or explicit instructions to treat the fetched content as untrusted data, allowing potential embedded commands to be interpreted by the agent.
  • Capability inventory: The skill includes write access to X, allowing the agent to post tweets, threads, and media using oauth.post endpoints in SKILL.md.
  • Sanitization: There is no evidence of sanitization or filtering of the fetched social media content before it is used for sensitive tasks such as voice modeling or content generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:58 PM
Security Audit — agent-trust-hub — x-api