fetch-tweet
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches tweet data from the external service
api.fxtwitter.com. This is a well-known open-source proxy used to access Twitter content programmatically without requiring official API credentials or JavaScript. - [INDIRECT_PROMPT_INJECTION]: The skill processes external content (tweet text), which creates a potential surface for indirect prompt injection if the fetched text contains malicious instructions intended to influence the agent's behavior.
- Ingestion points: Tweet text and metadata are retrieved from the external
fxtwitter.comAPI inscripts/fetch_tweet.pyand returned to the agent context. - Boundary markers: No specific boundary markers or "ignore instructions" warnings are included in the script's output to isolate the external content.
- Capability inventory: The skill is limited to fetching and formatting data; it does not possess capabilities for file writing, sensitive data access, or arbitrary command execution.
- Sanitization: The script performs structured field extraction but does not sanitize the contents of the tweet text for instructions or injection patterns.
Audit Metadata