deployment-readiness

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official vendor tools such as harness_list and harness_get to interact with the Harness MCP server for information retrieval.- [SAFE]: The instructions focus on read-only assessment and recommendation tasks, with explicit warnings not to perform state-changing operations like running or debugging pipelines.- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the instructions or metadata.- [SAFE]: Resource access is restricted to the specific vendor environment, which is appropriate for the skill's stated purpose of auditing deployments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 09:59 AM
Security Audit — agent-trust-hub — deployment-readiness