manage-slos
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions focus on legitimate use of the Harness MCP server for site reliability tasks. It does not attempt to bypass safety guidelines or perform unauthorized actions.
- [DATA_EXFILTRATION]: No exfiltration patterns were detected. The skill interacts with the Harness platform using specific tool calls (harness_list, harness_get) to pull data for user-initiated triaging and reporting.
- [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or scripts executed by this skill. It operates entirely through predefined MCP tool interactions.
- [CREDENTIALS_UNSAFE]: The skill correctly uses placeholders (e.g., , ) for identifiers and does not contain hardcoded secrets or sensitive environment access.
Audit Metadata