search
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The shell script
scripts/search.shperforms network requests tohttps://api.inspiro.top/search, an external domain not on the trusted vendors list. - [INDIRECT_PROMPT_INJECTION]: The skill fetches content from the web which could contain malicious instructions designed to influence agent behavior.
- Ingestion points: Search result snippets and page content returned by the Inspiro API.
- Boundary markers: The skill does not implement delimiters or safety instructions to distinguish retrieved content from system prompts.
- Capability inventory: The skill's capabilities are limited to network requests via
curland do not include file system access or arbitrary code execution. - Sanitization: No sanitization or filtering is applied to the retrieved web content before it is provided to the agent.
Audit Metadata