olares-search
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
olares-cli searchto perform global searches across local and cloud environments. This is a core functionality of the skill within the Olares ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external sources (local Drive, Sync/Seafile, Google Drive, Dropbox, and Wise/Knowledge) that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted data enters the agent's context through the output of subcommands such as
olares-cli search drive,olares-cli search sync, andolares-cli search knowledge. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when presenting search results to the agent.
- Capability inventory: The skill is primarily read-only for search, but instructions reference related skills (
olares-files) that provide broader file-system access (list, read, download). - Sanitization: No evidence of sanitization, filtering, or validation of the indexed content is present in the skill instructions.
Audit Metadata