dsh-taintguard
Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.
当工具结果包含不可信内容时将代理标记为已污染，对随后的高权限调用进行拦截，并在所有模式下拒绝将凭据传递给可联网的工具。
How to install
dsh plugin add github:sashankh/dsh-taintguard About
dsh-taintguard Indirect prompt-injection guard for DeepSeek Harness. An agent that browses the web or reads a repository puts third-party text into the same channel that carries its operator's instructions. A model has no reliable way to tell them apart, so a page, a README, or an MCP tool result can ask the agent to run a command or post a file somewhere. This plugin does not try to make the model immune to that. It narrows what the retrieved text can reach: it marks the agent once a tool result arrives from an untrusted source, gates the privileged calls that follow, and refuses outright whe…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-16
- Created
- 2026-08-16
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- agent-security, ai-security, deepseek-harness, dsh, dsh-plugin, guardrails, prompt-injection
Related plugins
dsh-auto-review
PerryLink/dsh-auto-review
Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.
dsh-passwords
slywalker2006/dsh-passwords
Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.
dsh-auth-gate
TecFancy/dsh-auth-gate
Login gate for the dsh web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI (dsh.bundle manifest since 0.4.1, one-command `dsh plugin add` mounting).
dsh-approval-llm
Letter2025/dsh-approval-llm
Model-based permission approval: an approval-request answerer backed by a separate reviewer model.