salvage
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were identified during the analysis of the skill.
- [DATA_EXPOSURE]: The skill manages session state by reading and writing to files within the .oh/ directory. This activity is restricted to the local workspace and is essential for the tool's stated purpose of session persistence.
- [COMMAND_EXECUTION]: The skill integrates with specific Model Context Protocol (MCP) tools, such as 'oh_search_context' and 'oh_record_metis'. These tool calls are used for knowledge retrieval and storage within the agent's environment and do not constitute arbitrary command execution.
Audit Metadata