Skip to content

moltguard

Detect and block prompt injection attacks hidden in long content (emails, web pages, documents) using OpenGuardrails SOTA detection

Open source page

Install command

$ npx clawhub@latest install ThomasLWang/moltguard

Core Content (SKILL.md)

When to use

  • Detect and block prompt injection attacks hidden in long content (emails, web pages, documents) using OpenGuardrails SOTA detection

CLI tools

  • npx clawhub@latest install ThomasLWang/moltguard

How to use

  • Install the skill with the command shown above.
  • Read SKILL.md and identify the trigger conditions.
  • Invoke the skill when the task matches its scope.
  • Fallback to direct execution if the skill is unavailable.

Categories & tips

  • Review SKILL.md headings for scenarios and feature boundaries.
  • Prioritize exact keyword matches before trying alternatives.
  • Use tags and owner context to avoid similar-name confusion.

Error handling

  • If no relevant section is found, ask a clarifying question.
  • If install fails, retry with network and permission checks.
  • If capability is missing, continue with a manual fallback plan.

moltguard

Detect and block prompt injection attacks hidden in long content (emails, web pages, documents) using OpenGuardrails SOTA detection

Related skills

-