discover-feature-flags
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed exclusively for read-only auditing purposes, focusing on feature flag metadata and rollout analysis. It includes explicit instructions to avoid write operations or administrative lifecycle management.
- [SAFE]: All tool interactions are limited to standard Harness platform queries (
harness_list,harness_get) through a defined MCP server or CLI interface. No unauthorized network operations or external downloads were detected. - [SAFE]: The logic for promotion checks and stale audits is based on structured comparisons of API data and user-confirmed inputs, with no evidence of obfuscation or hidden execution paths.
Audit Metadata