reef-prompt-guard

Web & Frontend Development
v1.0.0
Benign

Detect and filter prompt injection attacks in untrusted input.

660 downloads660 installsby @staybased

Setup & Installation

Install command

clawhub install staybased/reef-prompt-guard

If the CLI is not installed:

Install command

npx clawhub@latest install staybased/reef-prompt-guard

Or install with OpenClaw CLI:

Install command

openclaw skills install staybased/reef-prompt-guard

or paste the repo link into your assistant's chat

Install command

https://github.com/openclaw/skills/tree/main/skills/staybased/reef-prompt-guard

What This Skill Does

Scans untrusted text for prompt injection before it reaches an LLM. Applies context-aware scoring multipliers based on input source, with stricter thresholds for high-risk origins like web scrapes or email. Covers injection, jailbreaks, exfiltration, privilege escalation, and hidden instruction techniques.

Source-aware scoring lets you apply stricter thresholds for high-risk inputs like web scrapes without writing separate filter logic for each channel.

When to Use It

  • Filtering email bodies before LLM summarization
  • Screening Discord bot messages for jailbreak attempts
  • Validating web-scraped content before passing to an agent
  • Blocking injection in sub-agent output pipelines
  • Protecting API request handlers from malicious user prompts

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Filtering email bodies before LLM summarization

AGENT
  1. 1Filtering email bodies before LLM summarization
  2. 2Screening Discord bot messages for jailbreak attempts
  3. 3Validating web-scraped content before passing to an agent
  4. 4Blocking injection in sub-agent output pipelines
  5. 5Protecting API request handlers from malicious user prompts
OUTPUT
Detect and filter prompt injection attacks in untrusted input.

Share this skill

Security Audits

VirusTotalBenign
OpenClawBenign
View full report

These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.

Details

LanguageMarkdown
Last updatedFeb 25, 2026