플러그인

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

스킬과 MCP 설정에서 프롬프트 인젝션, 동형 문자(homoglyph), 숨겨진 유니코드, 위험한 셸 명령, 자격 증명 유출을 스캔

Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets