Verification
L1 · Found
Risk
Critical
Health
Active
Trust
Unrated
What it doesAI
DSH guardrail plugin that intercepts agent tool-call inputs, matching dangerous patterns to deny or warn, with a rule management panel.
- Deny/warn interception on tool-call string matching
- 11 built-in high-risk rules, toggleable actions
- React rule panel with test, audit, hot-reload
AI-generated from the repo README — for reference only.
Installation
dsh plugin --profile web add github:jypjypjypjyp/dsh-guardrailInstall method: GitHub · no verification record (L1-L5)
Compatibility
| DSH Version | Status |
|---|---|
| not stated | no verification record |
Requirements
- • Node.js: not stated
- • DSH: not stated
- • External credentials: none detected
Security Report
Automated static scan, not manual review.
DSH.SO VETPASSED17b937
Security reviewAutomated review · daily
PASSED
Vet static analysis found no suspicious behavior — verdict is clean.
0 critical·0 high·0 medium·100 score
plugin version
0.0.1dsh manifestscanned commit
17b93770024d2026-08-25latest commit
17b93770024dvet verdict
clean · gitscore 100Vet is an AST static scan (npm artifact or git source).
`[](https://www.dsh.so/artifact/dsh-guardrail/)`Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
Risk details
No critical or warning findings.
Activity
Last commit 2026-08-25 · activity: Active
• Repo created: 2026-08-25
• Stars: ★ 1 · Forks: 0
• Health: Active — committed within last 30 days