Loading...
Loading...
Found 3 Skills
Google Model Armor: Filter user-generated content for safety.
Detect and defend against indirect prompt injection hidden in web pages, documents, and images consumed by an agent, via content extraction (HTML/PDF/OCR), normalization, and scanning with LLM Guard's PromptInjection scanner or Hugging Face Prompt Guard 2. Use when an agent ingests untrusted external content and you need to screen it for injected instructions before the LLM processes it.
Reduce negative-constraint and session-history leakage when a discarded proposal or user correction is echoed into final artifacts as a ‘without X’ label, rejected-option explanation, or process residue. Use for 此地无银三百两式 output in prose, code, metadata, and handoffs, including later requests to finish, commit, publish, or open a PR after iterative work; not for ordinary deletion, deprecation, migration, or requirements where the exclusion itself is material.