DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.
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 session log (approval/asked -> autoReview/verdict -> approval/decided).
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
Read-only security & compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and local configuration audit with redacted, reproducible reports.
让你通过浏览器安全地远程使用 DeepSeek Harness:登录、MFA 两步验证、角色权限和远程文件预览。 | Use DeepSeek Harness securely in a remote browser with login, MFA, roles, and remote file preview.
Double-check before you ship: grill the requirements, test the implementation, prove the delivery. An engineering-discipline bundle for DeepSeek Harness.
DeepSeek Harness (DSH) plugin: a read-only ledger for the plugins you already have installed — a capability inventory with file:line evidence, declared-vs-detected reconciliation, cross-profile version drift, and a diff of what changed since the last scan.
Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events
Login gate for the DeepSeek Harness (dsh) web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI. | DeepSeek Harness (dsh) 网页版登录门插件:账号口令或共享令牌认证、会话 cookie、登录限速,附用户管理 CLI。
PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled storage domain, never log plaintext, and expose /mask and the mask_test tool