Plugins

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.

Auditoria de segurança local: configuração, origem dos plugins, sessões, exposição de rede — relatório de risco somente leitura e com dados sensíveis ocultos.

Alternative plugin market for DSH: curated catalog plus live GitHub browsing, zh/en cross-language search, a fail-closed pre-install static security audit with an install-hook block, and per-plugin README viewing with garbled-encoding repair.

Tested-curation lab for DSH plugins: every entry passes real install/static-scan gates in an isolated environment, with full logs and reproduction commands (Chinese-first).

Plugin de provedor opcional para o dsh-skill-pack-security: registra a edição skills/ (zh) ou skills-en/ (en) do pacote em ctx.skills. Ambas as edições vêm embutidas em pack/