writing-agent-behavior

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are focused on documentation best practices for defining agent conduct. The content does not contain any prompt injection attempts, data exfiltration patterns, or obfuscated code.- [COMMAND_EXECUTION]: The skill references a CLI tool named agentbehavior for validating specifications. The instructions include a safeguard advising the user not to install the command without authorization if it is not already present, which follows security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 08:24 PM