wikipedia-search
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process information from Wikipedia, an external source where content can be modified by third parties.
- Ingestion points: The
wikipedia_get_articletool fetches article text from external Wikipedia servers. - Boundary markers: There are no specific instructions or delimiters defined to help the agent distinguish between informational content and potentially malicious instructions embedded within Wikipedia articles.
- Capability inventory: The skill itself is restricted to reading and citation tasks; it does not possess capabilities for file modification, command execution, or sending data to unauthorized external endpoints.
- Sanitization: The instructions do not define any sanitization, filtering, or validation logic for the content retrieved from the external source.
Audit Metadata