harness-agents-md

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is documentation generation (AGENTS.md and CLAUDE.md) based on local project metadata and file structure.
  • [SAFE]: File system access is restricted to reconnaissance within the project root and specific vendor-controlled directories such as .nextstage-harness/ and .agents/skills/.
  • [SAFE]: External tool references, such as the @nextstage-brasil/harness package, originate from the official vendor infrastructure and are used for standard synchronization and documentation tasks.
  • [SAFE]: No network exfiltration patterns, credential harvesting, or unauthorized privilege escalation mechanisms were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 08:16 PM
Security Audit — agent-trust-hub — harness-agents-md