x-api
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the X API (e.g., search results, timelines) which is then used for tasks like voice modeling or content generation, creating a surface where malicious instructions in tweets could influence agent behavior.
- Ingestion points: Data is fetched via
requests.getfromapi.x.comendpoints inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to differentiate between the retrieved data and its primary instructions.
- Capability inventory: The skill utilizes
requestsfor network operations and demonstrates local file reading for media uploads inSKILL.md. - Sanitization: The provided examples do not include logic for filtering or sanitizing the content of fetched tweets before they are processed by the agent.
Audit Metadata