94 results
Outbound LLM request header modification for DeepSeek Harness (DSH): client-identity header presets (Codex / Claude Code / opencode), per-request dynamic headers, X-Stainless fingerprint stripping, URL rewriting and Anthropic body patching at the fetch transport layer.
System tray support for DSH Desktop: tray icon plus settings to hide the main window on minimize or close, with self-healing boot-time injection and an injection management panel.
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.
全局提示注入 / 上下文病毒（context virus）防御插件：tools/pre-execute 扫工具参数、tools/post-execute 扫工具结果、agent/pre-step 扫进入模型前的消息并注入金丝雀守卫、llm/stream 出站消毒；支持 block / quarantine / monitor 三模式、磁盘化可演进病毒库（学习/导入/导出）与审计日志。纯 JS 无原生依赖，profile 层挂载，对所有预设与子代理全局生效。
Global and workspace rules for DeepSeek Harness agents: configurable storage paths, system-prompt injection and a rules_read model tool.
Automatic TMCRA recall, injection, and role-separated writeback for DeepSeek Harness
Spike: channel-grouped session view for DeepSeek Harness — sidebar tab injection + session-projection data path (RFC dsh-channel-spec)
Independent same-host session-to-session interconnection for the DeepSeek Harness. In-process broker delivery, name (title) addressing, dormant-session wake, durable mailbox, anti-loop budget. Inspired by @dpskh/a2a injection idiom; no hub or network mesh.
A safe external-skill discovery and adoption bundle for DeepSeek Harness
Task-to-skill pairing with a laziness ladder and a safe install cellar. Never overpours, never serves untasted. DSH · Claude Code · Codex
A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API
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.
Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions — with structured entry tags (kind/status), a grouped summary view, automatic context injection, an archive on clear, and an optional read-only web panel
Cairn — long-term memory for the DeepSeek Harness: persistent cross-session memory (store, tools, auto-extraction, context injection) as one installable profile bundle
Hybrid memory plugin for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md, read on demand, zero context cost) + L2 searchable knowledge base (one-fact-per-file, SQLite FTS5) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and approved Agent Hub documents. No automatic injection. Data lives on D drive, never C.
DSH Obsidian Sync - DSH Cordis plugin: on-demand Obsidian knowledge-base search + DSH session archiving following your vault's existing PARA rules (zero token injection, in-process fs, inverted index, idempotent upsert)
Cross-session long-term memory for the DeepSeek Harness: a two-phase extraction/consolidation pipeline over a file-based memory workspace, recall injection, a citation feedback loop, lease-based job semantics, plus a settings page, a sidebar status panel and a memory viewer.
请求头注入插件：按 host 规则注入 HTTP 请求头（多条规则各自独立头集合，同名头覆盖原值），绕过目标站点客户端校验；其余请求零影响。默认规则预设 agentrouter.org → User-Agent: RooCode/0.15.0 典型用例
DeepSeek Harness plugin: Set AI Language via system prompt injection
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII redaction, and a local configuration security audit that emits redacted, reproducible risk reports.
Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin and gates privileged tool calls that follow untrusted content
DSH plugin: a codex-style apply_patch tool (*** Begin Patch / *** Update File / *** Add File / *** Delete File) injected into the model toolset through DSH's built-in sandbox, with a settings card to choose injection scope (off / GPT models only / all models).
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