acture-hard-donts
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation used to guide an AI agent during code reviews. It does not include any scripts, executable commands, or external network requests.
- [SAFE]: The instructions explicitly advocate for security best practices. Specifically, Point 5 warns against using
eval()on LLM-produced strings to prevent injection attacks, and Point 10 emphasizes that LLM calls must not bypass authorization or validation logic. - [NO_CODE]: There are no code files, package dependencies, or remote scripts associated with this skill. It functions purely as a reference for architectural and security constraints.
Audit Metadata