x-api
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill fetches content such as tweets, user profiles, and mentions from the X API. This data is created by external users and could contain malicious instructions designed to influence the agent's behavior when processing the retrieved information.
- Ingestion points: SKILL.md (via
requests.getcalls to search and timeline endpoints) - Boundary markers: None identified; the code snippets show raw API response processing without delimiters or specific instructions for the agent to ignore embedded commands.
- Capability inventory: The skill enables network operations (POST/GET) to the X API and file system access (reading
image.pngfor uploads). - Sanitization: No evidence of sanitization, filtering, or validation of the retrieved tweet content before it enters the agent's context.
Audit Metadata