unStone/dsh-xray

unStone★ 3PythonLast synced: 2026-08-21

Open on GitHub

X-ray for DeepSeek Harness plugins: declared capabilities vs actual behavior. Registry + static scanner + badges.

README excerpt

dsh-xray — capability cards for DeepSeek Harness plugins What a dsh plugin declares vs. what its code actually does — with file:line evidence. English · 简体中文 🔍 Registry · 📊 Report · 📈 Levels explained · 📖 How dsh plugins work Site available in English / 简体中文 / 日本語 89% of scanned plugins carry a powerful capability surface · 76% patch the dsh runtime itself · 6,800 plugins scanned, refreshed daily Why The dsh-plugin ecosystem went from 200 to 7,000+ repos in 30 days . Plugins run arbitrary code inside your agent runtime: they can rewrite your system prompt ( system-prompt/assemble ), intercept every API call ( api/gate ), spawn subprocesses, read GITHUB TOKEN from your env, and even patch the runtime itself ( manifest.bundle.patch ). Today nothing surfaces any of that before you install. dsh-xray statically scans every plugin in the ecosystem and publishes a capability card : Dimension Examples Declared surface manifest , injected services, registered tools, hooks Powerful capabilities systemPrompt / apiProxy / subprocess injection, tools/pre-execute gate, runtime patches Sensitive behavior exec / eval / base64 decode in shipped code, install-time scripts, outbound domains, cred…

View full README on GitHub →
Tools / Devagent-securityai-agentsai-securitycapability-analysiscordisdeepseek-harnessdshdsh-plugin

Category