x-api

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a workflow that ingests untrusted data from the X (Twitter) platform, creating an attack surface for indirect prompt injection.
  • Ingestion points: Data is retrieved from api.x.com through search queries and timeline reads in SKILL.md.
  • Boundary markers: The skill does not provide delimiters or specific instructions to the agent to treat fetched tweet content as untrusted data or to ignore instructions contained within it.
  • Capability inventory: The skill possesses the capability to post content back to the same platform via oauth.post to api.x.com/2/tweets, which could be exploited if an injected instruction directs the agent to post unauthorized content.
  • Sanitization: No sanitization or filtering logic is present in the code snippets to validate or clean the external data before it is processed for tasks like voice modeling.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 11:30 AM
Security Audit — agent-trust-hub — x-api