dsh-risk-gate
by — · leetom314/dsh-risk-gate
★ 0 Stars
⑂ 0 Forks
Original language: English
About
Semantic risk grading and progressive authorization: classifies tool calls into safe/risky/redline, asks before irreversible actions, auto-allows only approved-and-succeeded signatures.
Compatibility
Versions
| Latest version | Published | Size |
|---|---|---|
| 0.1.0 | — | — |
Similar plugins
Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and ap
★ 0
dsh plugin --profile web add dsh-egress-guardFine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions,
★ 0
↓ 436/wk
dsh plugin --profile web add @mrweicodes/dsh-permgateAuto-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-guardTurns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations,
★ 0
dsh plugin --profile web add dsh-permission-matrixString-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 shuxue6662-a11y
Zero-interruption audit and fuse blocking for DeepSeek Harness: silently records every tool call with deterministic risk scoring, cumulative-risk bonuses, risk-level breakdowns and retention-based cle
★ 0
MIT
TypeScript
Aug 17, 2026
dsh plugin --profile web add dsh-risk-guard