DSH Hub

PensiveFei/dsh-secure-audit

dsh-secure-audit

BundleWorkflow85 GitHub stars· updated 2026-10-27

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

Install

npx @deepseek-ai/dsh plugin --profile web add github:PensiveFei/dsh-secure-audit

Restart `dsh web` after install. Bundle APIs can change during the developer preview.

README badge

dsh-secure-audit DSH Hub badge
[![DSH Hub](https://dshhub.dev/badge/dsh-secure-audit.svg)](https://dshhub.dev/plugins/dsh-secure-audit)

Paste this into your README. The star count updates with every catalog sync.

From the README

Excerpt from PensiveFei/dsh-secure-audit, cleaned of badges and images.

dsh-secure-audit

Disclaimer. This is an unofficial third-party tool. It is not affiliated with, endorsed by, or sponsored by DeepSeek. "DeepSeek" and "DeepSeek Harness" are trademarks of their respective owners; they are referenced here only to describe what this plugin runs against.

Read-only security and compliance plugin for DeepSeek Harness (DSH).

Also listed in awesome-dsh-plugin · Awesome DeepSeek Harness

Compatibility

  • Peer dependency: @deepseek-ai/dsh-tools >= 0.1.2-alpha.2, provided by the DSH runtime.
  • Tested against @deepseek-ai/dsh-tools 0.1.2-alpha.2. DSH itself is pre-1.0; pin your DSH version and re-run security_audit after upgrading either side. Release notes state the DSH snapshot each version was tested against.
  • No install-time scripts and no build step; the shipped source is the artifact.

Four tools and one skill:

CapabilityToolWhat it does
Prompt-injection detectionsecurity_scan_textRule engine (English + Chinese) with LRU cache, fail-open timeout (configurable fail-closed), a pluggable model classifier, and an obfuscation-resistance layer (zero-width/full-width/homoglyph normalization + bounded base64 decoding, ruleset v5). Returns allow / review / block, a riskLevel, and an inputSha256 for replayable decisions.
PII redactionsecurity_redact_textMasks the supported CN mobile, CN ID card, CN bank card, email, IPv4, API key, and URL-credential patterns; other sensitive types still need review.
Structured JSON redactionsecurity_redact_jsonRecursively redacts sensitive values inside JSON by key name (api_key, token, secret, password, authorization, ...) plus a PII fallback on other values. The structure is preserved — safe to hand tool-call arguments or session context to a third-party model.
Local security auditsecurity_audit11 read-only checks across config / sessions / plugins / paths / network / env / host, mapped to OWASP LLM + Agentic Top 10, with `quick
Security review skillsecurity-reviewRegistered at runtime via the optional skills service; teaches the agent how to use the tools and explain verdicts.

The plugin never writes, deletes, or executes anything on the audited system. That is a hard constraint of the codebase, not a convention: the audit/redaction/scan code paths perform reads only; the single write path in lib/ is the opt-in logFile audit log in lib/logger.js (append-only JSONL, disabled by default).

Install

The plugin has no build step and no install scripts. index.js and lib/ are the shipped artifact; nothing compiles, so there is nothing to run at install time.

# from a tarball (attached to every GitHub release)
dsh plugin add ./dsh-secure-audit-0.1.0.tgz

# from git source (no build runs; pin the commit)
dsh plugin add github:PensiveFei/dsh-secure-audit#<commit>

…

Related plugins