searxng-api
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill's purpose is to retrieve external data from the web via a meta-search engine, which introduces a risk of indirect prompt injection. * Ingestion points: External content from the results list (title, content, and answers fields). * Boundary markers: Absent; there are no instructions provided to the agent to isolate or sanitize the external data. * Capability inventory: Documentation for GET/POST network requests to a search API. * Sanitization: None described in the usage guidelines.
- No Code (INFO): No executable scripts (Python, JavaScript, Shell) or binary files were detected; the skill consists entirely of Markdown documentation.
Audit Metadata