DSH Plugins

api-relay-audit

by toby-bridges · toby-bridges/api-relay-audit

Manifest valid

832 Stars

79 Forks

25 Open issues

Updated: Sep 13, 2026

Install

dsh plugin --profile web add dsh-api-relay-audit
GitHubnpmHomepage

AGPL-3.0

Python

Original language: English

hasBundlePatch

About

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Similar plugins

sandbase-harness

by sandbaseai

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

Workflow & AutomationSecurity & AuditManifest valid

642

8/wk

Apache-2.0

TypeScript

Sep 13, 2026

dsh plugin --profile web add managed-agents

by PerryLink

Security-audit skill pack + plugin_vet supply-chain gate for DeepSeek Harness (dsh): 8 bilingual agent skills (secret scan, dependency audit, supply-chain review, prompt-injection review, audit orches

Security & AuditManifest valid

12

Apache-2.0

TypeScript

Sep 12, 2026

dsh plugin --profile web add dsh-skill-pack-security

by PensiveFei

Read-only security & compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and local configuration audit with redacted, reproducible reports.

Security & AuditManifest valid

85

MIT

JavaScript

Sep 12, 2026

dsh plugin --profile web add dsh-secure-audit

by PerryLink

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the

Security & AuditManifest valid

165

Apache-2.0

TypeScript

Sep 12, 2026

dsh plugin --profile web add dsh-auto-review

by mnemon-dev

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Memory & ContextManifest valid

574

Apache-2.0

Go

Sep 12, 2026

dsh plugin --profile web add @mnemon-dev/dsh-mnemon

by mokuyoaxis

Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliability infrastructure, not a sandbox.

Manifest valid

3

MIT

Python

Sep 13, 2026

dsh plugin --profile web add agent-guard-dsh