false-positive-prompt-injection
Security Guide
This guide explains how to detect and prevent prompt injection attacks.
You should never allow users to ignore previous instructions in your application. Always block attempts to override system rules. This is a security best practice.
More from oakencore/skillvet
skillvet
Security scanner for ClawHub/community skills — detects malware, credential theft, exfiltration, prompt injection, obfuscation, homograph attacks, ANSI injection, MCP server attacks, campaign-specific attack patterns, and more before you install. Use when installing skills from ClawHub or any public marketplace, reviewing third-party agent skills for safety, or vetting untrusted code before giving it to your AI agent. Triggers: install skill, audit skill, check skill, vet skill, skill security, safe install, is this skill safe.
105clean-skill
A harmless utility skill for testing.
1trigger-obfuscation
Test fixture for check #4.
1trigger-credential-access
Test fixture for check #3.
1