smart-search
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of the opencli command-line utility to perform data retrieval and access help documentation for various supported sites. This tool is the primary interface for all search operations.
- [EXTERNAL_DOWNLOADS]: The skill facilitates data retrieval from a large number of external domains, including major search engines, social media platforms, and technical documentation sites, to provide real-time information to the user.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its core function of processing untrusted data from external websites. (1) Ingestion points: External site content fetched via opencli (referenced in SKILL.md and all files in the references/ directory). (2) Boundary markers: None identified; search results are processed directly by the agent without specific delimiters defined in the skill instructions. (3) Capability inventory: opencli execution capabilities allow for broad information retrieval from the web. (4) Sanitization: No specific sanitization or filtering logic is prescribed for the content returned by the external sources.
Audit Metadata