DSH插件商店

api-relay-audit

toby-bridges

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

dsh-jev-interceptor

AskTheWay

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

dsh-riskproof

onlyqzq

Risk-aware approval layer for high-risk AI Agent tool calls

PSA-core

SiliconPsycheLabs

PSA is a multi-classifier behavioral analysis engine for LLM responses. It classifies every sentence into behavioral postures, then derives metrics from the posture sequences to detect adversarial stress, sycophancy, hallucination risk, persuasion techniques, and input pressure — in real time.

dsh-plugin-security-review

ateen18

Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.

dsh-auto-review

Jelee0145

Codex-style automated approval review for DeepSeek Harness: an isolated reviewer subagent decides sandbox escalations by intrinsic risk and user authorization. Community Beta — not an official DeepSeek AI plugin.

skill-security-guard

rrrrrredy

Static security scanner for agent skills: A-F risk rating, safe zip scanning, CI-tested rules