Is Openclaw Skill Vetter MCP server safe?
Not recommended.
Hidden from default browsing. Significant findings or unreachable.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
2 medium
- Code scan17 source files scanned15/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
Findings (2)
- mediumeval / new Function used
exec.evalopenclaw_skill_vetter_mcp-1.1.2/src/openclaw_skill_vetter_mcp/backends/mock.py: …r" - `markdown-formatter` — MEDIUM: eval() in code + broad fs-write permission …
- mediumsubprocess with shell=True
exec.shell-trueopenclaw_skill_vetter_mcp-1.1.2/src/openclaw_skill_vetter_mcp/scanners/ast_check.py: … ) # subprocess.run(..., shell=True) / Popen(..., shell=True) i…
Overall 49/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Safer options for the same job
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedEstablishedC
- mcptoonMCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).not reviewedEstablishedA
- SkillsmithShare agent skills across your team, scan them for risk, and track what's actually used.not reviewedEstablishedB