xby-scan-code
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-scan-code
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-scan-code in DeepSeek Harness to install this plugin; source code is available at https://github.com/xby-skill/xby-scan-code.
About this plugin
AI-assisted coding is everywhere, yet the code it produces silently ships with hardcoded secrets, unsafe function calls, and misconfigured security logic. Manually auditing every line is slow and error-prone. xby-scan-code folds security review directly into your chat session: the moment you write or paste code, a targeted scan kicks in, eliminating the need for a separate IDE plugin or a CI queue.
Six capabilities ship out of the box: a full security pass (scanCode), a fast vulnerability-only sweep (scanVulnerabilities), detection of exposed keys and credentials (detectSecrets), actionable secure-fix suggestions for each finding (suggestSecureFix), and a regulatory-compliance check against GDPR, HIPAA, SOC 2, and PCI DSS (checkCompliance). A single set_xby_apikey call persists your key across restarts. Results appear as readable text in the conversation, and suggested fixes are copy-paste ready, so you never leave your current session.
It is built for solo developers pairing with AI coding tools, security-sensitive teams delivering under compliance frameworks, and engineering leads who want a quick pre-PR safety net. No extra services to stand up; install the plugin, drop in your API key, and start scanning.
Use Cases
- Quickly scan AI-generated code for hardcoded secrets or high-risk vulnerabilities
- Run a GDPR, HIPAA, or SOC 2 compliance check before submitting a pull request
- Get secure fix suggestions right in chat without switching to another security tool
Best For
- Solo developers writing code with AI assistance
- Security-sensitive teams delivering code under compliance frameworks
- Engineering leads who want a quick pre-PR security baseline check
Related Plugins
A network security red-team benchmark plugin for DeepSeek-V4.1/Flash featuring dual-layer kernel injection and zero-tool architecture for controlled model safety assessment.
A security red-team prompt plugin for DeepSeek-V4 that uses code-formal mapping and zero-trigger system prompts to enable unconditional output, intended for authorized testing and research only.
Adds an Auto approval mode on the official workspace-write sandbox, classifying semantic risks, asking when ambiguous, and denying destructive operations.
Undo/rollback system for DSH: config & plugin snapshots, one-click undo/redo/restore, message-level revert, secret masking, safe mode, and offline WebUI/GUI/CLI rescue tools for when DSH won't start.