semgrep-rule-creator
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing a framework for authoring, testing, and optimizing Semgrep rules.
- [EXTERNAL_DOWNLOADS]: The skill references documentation hosted on official GitHub repositories for Semgrep and Trail of Bits. These are well-known services and trusted organizations for security tooling.
- [COMMAND_EXECUTION]: Instructions guide the user to use the
semgrepCLI for validating rules and running tests. This usage is standard for the tool's purpose and does not involve malicious shell commands or unauthorized access. - [PROMPT_INJECTION]: The skill contains no instructions designed to subvert AI safety filters, extract system prompts, or override the agent's core behavioral guidelines.
- [REMOTE_CODE_EXECUTION]: Code snippets containing potentially dangerous functions like
eval()are provided as examples of vulnerable code for Semgrep to detect. They are part of the training documentation and are not meant for execution by the agent.
Audit Metadata