What it doesAI
Auto-injects chosen skills into DeepSeek Harness sessions per prompt or at session start, with settings and composer indicator.
- Inject skills per prompt or once at session start
- Settings page for choosing skills
- Composer indicator shows active injection
AI-generated from the repo README — for reference only.
Installation
dsh plugin --profile web add github:countossbot/dsh-skill-injectorsecurity scan passed · default branch source
Install method: GitHub · sandbox install verified (L5)
Verification & Compatibility
Records are archived per dsh version under test: each card shows the newest real L1–L5 verdicts on that version (static levels included; fall back to all-time newest with a carried note when absent).
External credentials (plugin-level): none detected
dsh 0.1.3-alpha.1current2026-09-07L5 · verified
- • Node.js: v24.14.0
- • DSH: 0.1.3-alpha.1
- • Plugin artifact: github · https://github.com/countossbot/dsh-skill-injector (version unstated)
ID: dsh-skill-injector@a5d617@dsh0.1.3-alpha.1 · profile: l4-sandbox
Issued: 2026-09-07 · expires: 2026-09-14
View checks & evidence
active in loader tree (151 entries)
Author badges
Embed the official badges in your README to showcase security & install-test status:
`[](https://www.dsh.so/artifact/dsh-skill-injector/)``[](https://www.dsh.so/artifact/dsh-skill-injector/)`Security Report
Automated static scan, not manual review.
Vet verdict is suspicious: findings need human review (exfiltration endpoints, file deletion, etc.).
1.0.0dsh manifestc7dae696c90b2026-09-07c7dae696c90bsuspicious · gitVet is an AST static scan (npm artifact or git source).
Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
Risk details
| Risk | Rule | Location | Description |
|---|---|---|---|
| high | R10 | package.json | install 钩子:package.json scripts.prepare(安装期任意代码执行面) |
| medium | R9 | helpers.js:3 | 正则嵌套量词(ReDoS 风险:(a+)+ 类指数回溯) |
| medium | R9 | helpers.ts:22 | 正则嵌套量词(ReDoS 风险:(a+)+ 类指数回溯) |
| medium | R9 | spider.js:11 | 正则嵌套量词(ReDoS 风险:(a+)+ 类指数回溯) |
| medium | R9 | extra-skills.ts:46 | 正则嵌套量词(ReDoS 风险:(a+)+ 类指数回溯) |
Activity
Last commit 2026-09-06 · activity: Active
• Repo created: 2026-09-06
• Stars: ★ 0 · Forks: 0
• Health: Active — committed within last 30 days
Source
Author README
View on GitHub ↗The author's original README.md from the repository — fetched live, unedited.
