34 results
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection
Press Enter to approve the sandbox permission-escalation prompt in the DeepSeek Harness WebUI instead of clicking the Allow once button.
DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费，峰时正好是上班时间。
DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.
SQL 优化模式：EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents（38k★ MIT）启发。
Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin and gates privileged tool calls that follow untrusted content
Bitwarden/Vaultwarden credentials in every DSH session: vault tools + proactive prompt guidance + a settings card for the master password.
Allowlisted git execution for DeepSeek Harness: a model-facing git tool that runs outside the file sandbox, with a settings page where the user ticks which git subcommands are permitted and, per path, which reads and writes are allowed, prompted or refused
Static trust audit for DeepSeek Harness plugins: capabilities, injected prompts, token cost, provenance, and a reproducible 0-100 trust score