tell-ai-what-not-to-do
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely documentation-based and provides best practices for prompt engineering. It does not contain any executable scripts, network operations, or file system access.
- [DATA_EXPOSURE]: The instructions explicitly promote security best practices by advising users to include negative constraints that prohibit the hardcoding of API credentials or file paths in generated code.
- [REMOTE_CODE_EXECUTION]: There are no external dependencies or remote script executions. The skill actually encourages minimizing supply chain risk by instructing the AI to avoid third-party libraries in favor of standard language libraries.
Audit Metadata