fetch-tweet
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs outbound network requests to api.fxtwitter.com to retrieve tweet metadata and content. While this is necessary for the skill's purpose, it involves communication with a non-whitelisted third-party service.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted data from X/Twitter.
- Ingestion points: External tweet text is retrieved from the api.fxtwitter.com API.
- Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions for the fetched content to prevent the agent from interpreting it as instructions.
- Capability inventory: The skill aggregates and processes (translates/analyzes) remote content, creating a surface where malicious text could influence the agent's behavior.
- Sanitization: There is no evidence of sanitization, escaping, or filtering of the retrieved tweet text before it is presented to the agent.
Audit Metadata