fetch-news-digest
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network operations to
api.worldmonitor.appto retrieve news digests. While this is the primary function of the skill, it involves sending requests to a non-whitelisted external domain. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from over 500 curated news feeds into the agent's context.
- Ingestion points: The agent retrieves data from the
https://api.worldmonitor.app/api/news/v1/list-feed-digestendpoint. - Boundary markers: The skill does not provide instructions to the agent to use boundary markers or to ignore instructions that might be embedded within the retrieved headlines or article summaries.
- Capability inventory: The skill uses
curlto make network requests; the broader risk depends on what other tools are available to the agent in its environment. - Sanitization: There is no mention of sanitization, validation, or filtering of the content received from the external API before it is processed by the agent.
Audit Metadata