run-pipeline
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured workflow for interacting with the Harness platform through authenticated MCP tools (
harness_search,harness_list,harness_execute, etc.). - [SAFE]: Implements mandatory human-in-the-loop confirmation steps for high-risk actions, specifically for production deployments, ensuring users verify versions and environments before execution.
- [SAFE]: All resource identifiers and inputs are handled through structured tool parameters rather than shell concatenation, reducing injection risks.
- [SAFE]: No evidence of obfuscation, remote code execution, or unauthorized data exfiltration was found in the instructions or metadata.
Audit Metadata