fetch-tweet
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches tweet data from api.fxtwitter.com, a well-known service for retrieving structured social media content.
- [PROMPT_INJECTION]: The skill processes external content from tweets which could theoretically contain malicious instructions (indirect prompt injection surface).
- Ingestion points: Data is fetched via WebFetch from the fxtwitter API in SKILL.md.
- Boundary markers: No specific delimiters or "ignore previous instructions" warnings are defined for the fetched content.
- Capability inventory: The skill uses WebFetch for data retrieval.
- Sanitization: No explicit sanitization or filtering of the fetched tweet text is implemented.
Audit Metadata