Skip to main content

skillnet

SkillNet enables users to search, create, and evaluate reusable agent skills, enhancing efficiency in task management.

Install this skill

or
2/100

Security score

The skillnet skill was audited on Feb 26, 2026 and we found 46 security issues across 3 threat categories, including 2 high-severity. Review the findings below before installing.

Categories Tested

Security Issues

low line 100

Access to hidden dotfiles in home directory

SourceSKILL.md
100skillnet download "<skill-url>" -d ~/.openclaw/workspace/skills
low line 107

Access to hidden dotfiles in home directory

SourceSKILL.md
107ls -la ~/.openclaw/workspace/skills/<skill-name>/
low line 110

Access to hidden dotfiles in home directory

SourceSKILL.md
110head -20 ~/.openclaw/workspace/skills/<skill-name>/SKILL.md
low line 113

Access to hidden dotfiles in home directory

SourceSKILL.md
113cat ~/.openclaw/workspace/skills/<skill-name>/SKILL.md
low line 116

Access to hidden dotfiles in home directory

SourceSKILL.md
116ls ~/.openclaw/workspace/skills/<skill-name>/scripts/ 2>/dev/null
low line 135

Access to hidden dotfiles in home directory

SourceSKILL.md
135ls ~/.openclaw/workspace/skills/
low line 136

Access to hidden dotfiles in home directory

SourceSKILL.md
136grep -rl "<keyword>" ~/.openclaw/workspace/skills/*/SKILL.md 2>/dev/null
low line 168

Access to hidden dotfiles in home directory

SourceSKILL.md
168--output-dir ~/.openclaw/workspace/skills
low line 171

Access to hidden dotfiles in home directory

SourceSKILL.md
171skillnet create --office report.pdf --output-dir ~/.openclaw/workspace/skills
low line 174

Access to hidden dotfiles in home directory

SourceSKILL.md
174skillnet create trajectory.txt --output-dir ~/.openclaw/workspace/skills
low line 178

Access to hidden dotfiles in home directory

SourceSKILL.md
178--output-dir ~/.openclaw/workspace/skills
low line 184

Access to hidden dotfiles in home directory

SourceSKILL.md
184skillnet evaluate ~/.openclaw/workspace/skills/<new-skill>
low line 201

Access to hidden dotfiles in home directory

SourceSKILL.md
201skillnet evaluate ~/.openclaw/workspace/skills/my-skill
low line 212

Access to hidden dotfiles in home directory

SourceSKILL.md
212skillnet analyze ~/.openclaw/workspace/skills
low line 220

Access to hidden dotfiles in home directory

SourceSKILL.md
220skillnet analyze ~/.openclaw/workspace/skills
low line 228

Access to hidden dotfiles in home directory

SourceSKILL.md
228skillnet evaluate ~/.openclaw/workspace/skills/skill-a
low line 229

Access to hidden dotfiles in home directory

SourceSKILL.md
229skillnet evaluate ~/.openclaw/workspace/skills/skill-b
medium line 232

Access to hidden dotfiles in home directory

SourceSKILL.md
232`skillnet analyze` only generates a report — it never modifies or deletes skills. Any cleanup actions (removing duplicates, pruning low-quality skills) require user confirmation before executing. Use
medium line 243

Access to hidden dotfiles in home directory

SourceSKILL.md
243| User provides a GitHub URL | Confirm with user → `skillnet create --github <url> -d ~/.openclaw/workspace/skills` → evaluate → read SKILL.md → apply |
medium line 244

Access to hidden dotfiles in home directory

SourceSKILL.md
244| User shares a PDF/DOCX/PPT | Confirm with user → `skillnet create --office <file> -d ~/.openclaw/workspace/skills` → evaluate → read SKILL.md → apply |
medium line 245

Access to hidden dotfiles in home directory

SourceSKILL.md
245| User provides execution logs or data | Confirm with user → `skillnet create <file> -d ~/.openclaw/workspace/skills` → evaluate → read SKILL.md → apply |
low line 264

Access to hidden dotfiles in home directory

SourceSKILL.md
264--output-dir ~/.openclaw/workspace/skills --model <model-name>
low line 265

Access to hidden dotfiles in home directory

SourceSKILL.md
265skillnet evaluate ~/.openclaw/workspace/skills/<new-skill> --model <model-name>
low line 320

Access to hidden dotfiles in home directory

SourceSKILL.md
320API_KEY="..." BASE_URL="..." skillnet create --prompt "..." --output-dir ~/.openclaw/workspace/skills
low line 391

Access to hidden dotfiles in home directory

SourceSKILL.md
391skillnet download "https://github.com/.../langgraph-supervisor-template" -d ~/.openclaw/workspace/skills
low line 394

Access to hidden dotfiles in home directory

SourceSKILL.md
394ls -la ~/.openclaw/workspace/skills/langgraph-supervisor-template/
low line 395

Access to hidden dotfiles in home directory

SourceSKILL.md
395head -20 ~/.openclaw/workspace/skills/langgraph-supervisor-template/SKILL.md
low line 397

Access to hidden dotfiles in home directory

SourceSKILL.md
397cat ~/.openclaw/workspace/skills/langgraph-supervisor-template/SKILL.md
low line 412

Access to hidden dotfiles in home directory

SourceSKILL.md
412skillnet create --github https://github.com/langchain-ai/langgraph --output-dir ~/.openclaw/workspace/skills
low line 413

Access to hidden dotfiles in home directory

SourceSKILL.md
413skillnet evaluate ~/.openclaw/workspace/skills/langgraph
low line 414

Access to hidden dotfiles in home directory

SourceSKILL.md
414cat ~/.openclaw/workspace/skills/langgraph/SKILL.md
low line 429

Access to hidden dotfiles in home directory

SourceSKILL.md
429--output-dir ~/.openclaw/workspace/skills
low line 430

Access to hidden dotfiles in home directory

SourceSKILL.md
430skillnet evaluate ~/.openclaw/workspace/skills/langgraph-code-pipeline
medium line 488

Access to hidden dotfiles in home directory

SourceSKILL.md
488- **Local-only persistence**: Downloaded skill files are written to disk (`~/.openclaw/workspace/skills/`) as plain text. They do not receive any system permissions and are not auto-loaded on future s
high line 258

Prompting for API key/token input

SourceSKILL.md
2583. If `API_KEY` is not configured → use the standard API_KEY ask template (see "Environment Variables & Credential Strategy").
medium line 320

Prompting for API key/token input

SourceSKILL.md
320API_KEY="..." BASE_URL="..." skillnet create --prompt "..." --output-dir ~/.openclaw/workspace/skills
high line 334

Prompting for API key/token input

SourceSKILL.md
334> I need an OpenAI-compatible API_KEY (used only for create/evaluate/analyze in this run). Optionally provide BASE_URL and model name (default gpt-4o). May I proceed with your key?
low line 293

External URL reference

SourceSKILL.md
293| `BASE_URL` | custom LLM endpoint | `https://api.openai.com/v1` |
low line 342

External URL reference

SourceSKILL.md
342> Would you like to use a custom LLM BASE_URL? (default `https://api.openai.com/v1`)
low line 356

External URL reference

SourceSKILL.md
356"BASE_URL": "https://api.openai.com/v1",
low line 410

External URL reference

SourceSKILL.md
410# to your configured LLM endpoint (https://api.openai.com/v1) using your API_KEY."
low line 452

External URL reference

SourceSKILL.md
452- **search / download**: Only the query string is sent to `https://api-skillnet.openkg.cn`. No local files, credentials, or personal data are transmitted. Downloaded content comes exclusively from `gi
low line 453

External URL reference

SourceSKILL.md
453- **create / evaluate / analyze**: Content is processed via the LLM endpoint you configure (`BASE_URL`, default: `https://api.openai.com/v1`). No data is sent to the SkillNet service for these operati
low line 454

External URL reference

SourceSKILL.md
454- **Local/air-gapped friendly**: Point `BASE_URL` to a local endpoint (e.g., `http://127.0.0.1:8000/v1` for vLLM, LM Studio, Ollama).
low line 477

External URL reference

SourceSKILL.md
477- **Before any `create` or `evaluate` call**, inform the user approximately how much data will be sent and to which endpoint (e.g., "~12K characters of skill content will be sent to https://api.openai
low line 478

External URL reference

SourceSKILL.md
478- **For sensitive content**, recommend using a local LLM endpoint (`BASE_URL=http://127.0.0.1:...`) to keep data on the user's machine.
Scanned on Feb 26, 2026
View Security Dashboard