Sensitive-information redaction for DeepSeek Harness: masks API keys, bearer tokens, JWTs, private keys and configured secrets in every tool result shown to the model, plus a redact_text tool and a redact RPC. · DSH 敏感信息脱敏插件:自动掩码工具输出中的 API key / token / 私钥 / 配置密钥。
메모리 및 지식 · 금융 데이터 · 서비스 연동
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DamonKoy/dsh-plugins#48110ca2779b59d36edec46c8aff97b6a50322aa&path:packages/dsh-secret-redactor
Static and runtime security guard for the DeepSeek Harness: scans plugins and workspaces for malicious code, context injection and token waste (block/warn/clean), intercepts dangerous runtime tool calls and prompt steps, and exposes /scan, plugin_scan, the scan web panel and a user-managed allowlist. Fully static analysis — never executes scanned code.
개발 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bigclawd/dsh-security-guard
Plugin manager for DeepSeek Harness: auto-discovers installed plugins, locates their npm / GitHub source, and provides snapshot-backed update and rollback from a Settings → Plugins tab.
Secret & dangerous-pattern scanner for DeepSeek Harness — a security_scan tool that finds leaked API keys, tokens, private keys and credential files, with full redaction.
기타 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ben7am1n/dsh-security-scan
Unofficial DeepSeek Harness vision plugin: when the main model receives an image-recognition request, it spawns a child agent switched to the SenseNova vision model (reusing the dsh-sensenova-freeapi credential), with a dedicated settings panel and a direct fallback path.
Agent 협업 · 시각 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:modesthub/dsh-sensenova-vision-aid
Share a selected range of chat messages as Markdown, HTML, TXT, or PNG (Web /share command, Session-header dialog, redaction, tool calls, subagent conversations, auto-save)
Agent 협업 · 생산성 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chrisx9z/dsh-session-chat-share