disguise-self
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised entirely of markdown-based instructions for content transformation. It does not require any additional Python or Node.js packages and lacks tools for network communication or file system manipulation.
- [SAFE]: The instructions include a comprehensive 'Pitfalls / Guardrails' section that explicitly prohibits the agent from altering facts, omitting requirements, or using the skill for deceptive purposes.
- [SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or hidden acrostics, were found within the text.
- [SAFE]: The metadata and tags, while broad (e.g., 'monitoring-and-protection'), do not contain malicious instructions or attempts to bypass agent safety protocols.
Audit Metadata