sk Skill · mukul975
detecting-indirect-prompt-injection
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.
Open on skills.sh ↗read 2026-09-15
- installs 8w
- 0
- 30-day movement
- starts with the next reading
- Related entries
- 1
- Connections
- 0
bashPythonllm-guardowasp-llmcontent-scanningmultimodalagent-securityllm-defenseindirect-prompt-injectionpythonai-security
- Host repository
- mukul975/Anthropic-Cybersecurity-Skills
- Version
- 1.0
- Licence
- Apache-2.0
- Host stars
- 33k
- Host language
- Python