fetch-tweet
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [DATA_EXFILTRATION]: Performs network operations to a non-whitelisted domain (
api.fxtwitter.com). The skill instructs the agent to useWebFetchto retrieve data from the third-party fxtwitter API service. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external tweet URLs, which could contain instructions intended to manipulate the agent. Ingestion points: Untrusted data enters the agent's context through the
WebFetchoutput fromapi.fxtwitter.comas defined inSKILL.md. Boundary markers: None. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the retrieved tweet text. Capability inventory: The skill usesWebFetchfor reading external data but does not include scripts with write, execute, or elevated file system capabilities. Sanitization: None. There is no instruction to sanitize, filter, or escape the fetched tweet content before it is displayed or processed.
Audit Metadata