dsh-guardian
by cdxiaodong · cdxiaodong/dsh-guardian
★ 3 Stars
⑂ 0 Forks
◎ 19 Open issues
Updated: Sep 10, 2026
TypeScript
Original language: English
About
Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.
Compatibility
Versions
| Latest version | Published | Size |
|---|---|---|
| 0.1.0-alpha.2 | — | — |
Similar plugins
Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 p
★ 0
dsh plugin --profile web add dsh-perm-guardTaints 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.
★ 0
dsh plugin --profile web add dsh-taintguardString-matches tool-call input arguments, blocks dangerous tool calls (deny) or allows them with an injected warning (warn), and ships a full rules-management panel.
★ 0
dsh plugin --profile web add @jypjypjypjyp/dsh-guardrailby Leeaoyin
Audits your agent harness stability using deepseek harness.
★ 0
MIT
TypeScript
Aug 17, 2026
dsh plugin --profile web add dsh-harness-auditby onlyqzq
Risk-aware approval layer for high-risk AI Agent tool calls
★ 7
Apache-2.0
TypeScript
Sep 10, 2026
dsh plugin --profile web add dsh-riskproofStatic and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web pan
★ 0
dsh plugin --profile web add dsh-security-guard