🏷️ The repository no longer carries a DSH topic (none of dsh-plugin / dsh-plugins / dsh). This page is a snapshot from indexing time; the repository is still reachable, but the plugin was removed from listings and maintenance pipelines.

agentguard

Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.

PluginSecurityDataMemoryFile

Verification

L3 · Install spec

stale

Risk

Out of scope

Health

Active

Trust

Silver

Install verification: sandbox install failed (L4) · tested on dsh 0.1.1-rc.2 · last checked 08-23Install verification details →

What it doesAI

Security guard for AI agents that blocks malicious skills, prevents data leaks, and protects secrets using detection rules and a trust registry.

Blocks malicious skills with 24 detection rules
Prevents data leaks and protects secrets
Runtime action evaluation with trust registry

securityAImemoryAIfileAI

Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.

Installation

dsh plugin --profile web add github:GoPlusSecurity/agentguard

Install method: GitHub · sandbox install failed (L4) · verified on dsh 0.1.1-rc.2

Verification & Compatibility

Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.

External credentials (plugin-level): none detected

Install compatibility matrix (rows = plugin versions〔latest 5〕, columns = dsh versions〔latest 5〕)

At-a-glance → evidence in the cards below

plugin ＼ dsh	dsh 0.1.1-rc.2
v1.1.28	·

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed

v1.1.28github2026-08-24

https://github.com/GoPlusSecurity/agentguard

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).

Author badges

Embed the official badges in your README to showcase security & install-test status:

Security Report

Automated static scan, not manual review.

DSH.SO VETMEDIUM9b72b9

Security reviewAutomated review · daily

MEDIUM

Vet verdict is suspicious: findings need human review (exfiltration endpoints, file deletion, etc.).

0 critical·22 high·308 medium

Version binding

plugin versionv1.1.28

scanned version1.1.28git2026-08-26

current versionv1.1.28version moved on

vet verdictsuspicious · npm

Vet is an AST static scan (npm artifact or git source).

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Risk details

Risk	Rule	Location	Description
high	R2	cron.js:13	require('node:child_process') 危险内置模块（执行/网络能力触达）
high	R2	cron.js:17	require('node:http') 危险内置模块（执行/网络能力触达）
high	R2	cron.js:18	require('node:net') 危险内置模块（执行/网络能力触达）
high	R13	policy.js:40	硬编码外联端点：Discord webhook（数据外泄端点）
high	R13	policy.js:41	硬编码外联端点：Slack webhook（数据外泄端点）

Heuristic static scan — may produce false positives. Review the source yourself before trusting.

Activity

Last commit 2026-09-29 · activity: Active

• Repo created: 2026-02-02

• Stars: ★ 463 · Forks: 67

• Health: Active — committed within last 30 days

Source

GitHub: github.com/GoPlusSecurity/agentguard

Plugin notes

What is the agentguard DeepSeek Harness plugin?

agentguard is a DeepSeek Harness plugin maintained by @GoPlusSecurity. It is cataloged on dsh.so as a Security plugin for Memory tasks, with a public GitHub source, declared install command, and automated static security scan.

How do I install agentguard?

Run dsh plugin --profile web add github:GoPlusSecurity/agentguard in a DeepSeek Harness (dsh) environment. The command is parsed from the plugin manifest and its install spec is verified (L3); runtime sandbox install testing may not have run yet.

How does the security scan relate to a manual audit?

The scan is automated static analysis of the repository source — a scalable first line of defense that can produce false positives and miss context; it is not a manual security audit. Before using a plugin, review the repository and installed permissions, and combine the scan with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-09-30