In this article
security-review-llm
| Field | Value |
|---|---|
| Kind | prompt |
| Source | .github/prompts/security/security-review-llm.prompt.md |
| Invocation | Slash command /security-review-llm |
| Interactive | Yes |
What it does
Run OWASP LLM and Agentic vulnerability assessments with codebase profiling
When to use it
Use this prompt when an LLM or agentic application needs paired OWASP LLM and agentic security assessments. Use the general security review when AI-specific applicability has not been established.
How to use it
Optionally provide the AI application scope. The prompt profiles the codebase, runs both assessment lenses, and produces evidence for qualified security review without exposing proprietary prompts, endpoints, or secrets.
Example usage
/security-review-llm scope=src/assistant
The prompt evaluates the sample assistant boundary and drafts combined LLM and agentic security findings.