custom-agent

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured workflow for managing custom agent files (.claude/agents/*.md). It includes a YAML frontmatter schema, tool restriction recommendations, and an audit checklist to ensure best practices like least-privilege tool access and clear agent descriptions. The instructions focus on file management and quality scoring without any suspicious or malicious operations. The disable-model-invocation: true flag in the frontmatter is a configuration setting that restricts how the skill is triggered, enhancing control rather than introducing risk. No unauthorized external downloads, credential harvesting, or obfuscation techniques were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 06:42 PM