effective-agent-skills

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a purely documentation-based resource that outlines design patterns, anti-patterns, and security checklists for creating agent skills. It lacks any executable scripts or external network requests.
  • [SAFE]: Static detection of prompt injection phrases is a false positive; keywords such as 'ignore previous instructions' are part of a security teaching section intended to help the agent identify vulnerabilities in other skills, not an attempt to override the current agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 11:08 PM
Security Audit — agent-trust-hub — effective-agent-skills