Help us improve
Share bugs, ideas, or general feedback.
From ruflo-aidefence
Scan inputs for prompt injection, unsafe content, and adversarial attacks using AIDefence
npx claudepluginhub erfwn81/velora --plugin ruflo-aidefenceHow this skill is triggered — by the user, by Claude, or both
Slash command
/ruflo-aidefence:safety-scan <input-text><input-text>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Scan content for prompt injection, jailbreak attempts, and unsafe patterns.
Applies C++ Core Guidelines to write, review, or refactor C++ code. Enforces modern, safe, and idiomatic practices for C++17/20/23.
Share bugs, ideas, or general feedback.
Scan content for prompt injection, jailbreak attempts, and unsafe patterns.
Before processing untrusted input (user submissions, API payloads, webhook data), scan it to detect prompt injection, adversarial content, or policy violations.
mcp__claude-flow__aidefence_is_safe with the input text for a boolean safe/unsafe resultmcp__claude-flow__aidefence_analyze for detailed threat classification and confidence scoresmcp__claude-flow__aidefence_scan for comprehensive multi-layer scanningmcp__claude-flow__aidefence_learn with confirmed threats to improve detectionmcp__claude-flow__aidefence_stats for detection rates and false positive metrics