prompt-guard

SKILLWorkflowcommunity
v0.0.0Orchestra-ResearchMITUpdated 3mo agoSource →

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
12kRepo stars
1Clients
1Formats
3mo agoLast update
Skill
AuthorOrchestra-Research
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptOpen (see Prompt tab)
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.