prompt-guard
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.
62
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./07-safety-alignment/prompt-guard/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
SKILL.md describes workflows that explicitly take third-party/free-form text (e.g., “web scraping, RAG docs”, “API responses”) into the classifier via `filter_third_party_data(data, ...)` / `batch_filter_documents(documents, ...)`, which would ingest outsider-authored content into LLM-adjacent context because the model/tokenizer run over that text at runtime.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The code calls AutoTokenizer.from_pretrained/AutoModelForSequenceClassification.from_pretrained using the meta-llama/Prompt-Guard-86M model (fetched from https://huggingface.co/meta-llama/Prompt-Guard-86M) at runtime, and that externally hosted model directly controls the skill's prompt-filtering behavior and is required for operation.
- Repository
- Orchestra-Research/AI-Research-SKILLs
- Commit
773a529
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.