x-api
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it is designed to ingest and process untrusted content from the X API, which can then be used in subsequent agent actions.
- Ingestion points: The skill fetches external data using endpoints like
https://api.x.com/2/tweets/search/recentandhttps://api.x.com/2/users/{user_id}/tweets(found in SKILL.md). - Boundary markers: The provided code snippets do not include delimiters or instructions to the model to ignore embedded commands within the fetched tweet content.
- Capability inventory: The skill has the capability to make network requests (
requests.get,oauth.post) and read local files (open("image.png", "rb")) for media uploads. - Sanitization: There is no evidence of sanitization or validation of the text returned from the X API before it enters the agent's context.
Audit Metadata