web-search
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides the ability to ingest untrusted data from the open web, creating a potential vector for indirect prompt injection.
- Ingestion points: The
webFetchfunction inSKILL.mdallows the agent to retrieve markdown content from any HTTPS URL. - Boundary markers: The instructions lack specific delimiters or guidelines for the agent to treat fetched web content as untrusted or to ignore instructions contained within that content.
- Capability inventory: The skill is designed to work within an agent environment that typically possesses further capabilities like file manipulation or command execution, which could be exploited if the agent obeys instructions found in fetched web pages.
- Sanitization: No sanitization, filtering, or validation of the fetched markdown content is described or enforced within the skill definition.
Audit Metadata