dsh-purge
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
23 results
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
DeepSeek Harness bundle for running API Relay Audit locally
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible, self-checksummed risk reports.
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
WebUI-managed encrypted credentials for DeepSeek Harness: one file, plaintext until a password is set, then AES-256-GCM ciphertext under an Argon2id-derived key with SHA3-256 fingerprints; per-request decryption, unlock lockout, leak-guard output redaction, and shipped-code integrity self-checks.
Correctover runtime security for DeepSeek Harness (DSH): CCS 7-dimension verification, command-injection/SSRF/credential-exfil blocking, Ed25519 receipts, audit-first. Install with `dsh plugin add dsh-correctover`.
Private, per-project system-prompt rules for DeepSeek Harness — matched by git remote URL, repo path, or cwd prefix; worktree-aware; never committed to the repository.
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness
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.
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
Portable DSH WebUI skill security inspection with local rules and optional model review
A runtime prompt-injection shield for DeepSeek Harness tool results.
Mingleng mcpguard for DeepSeek Harness 鈥?the first security plugin for DSH. Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell and credential leaks.
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。
Prompt-polish template injector for DSH: click ✨ in the composer to inject a 'polish my prompt' template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context.
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.
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
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection
对角巷 · 角色面具 — 一键切换AI人格,定制专属对话角色
Add mood-aware Japanese kaomoji to DeepSeek Harness (dsh) replies; prompt-injection plugin with a curated library from kaomojiya.org.
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.