wikipedia-search
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, hardcoded credentials, or obfuscated code were found in the skill definitions.
- [PROMPT_INJECTION]: Potential surface for indirect prompt injection from external data ingestion.
- Ingestion points: Wikipedia article content via the
wikipedia_get_articletool inSKILL.md. - Boundary markers: Absent; the instructions do not define specific delimiters for separating article content from agent instructions.
- Capability inventory: The skill is limited to information retrieval and citation formatting; no access to file writing, shell execution, or non-whitelisted network endpoints is present.
- Sanitization: Absent; the agent is expected to process the article content as provided by the tool.
Audit Metadata