Multi-agent AI skill orchestration — 13 skills, 7 lifecycle phases, from idea to post-release. Works with Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and any agent that reads Markdown or speaks MCP.
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 5
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 3d ago · see ecosystem CVEs →
- C · 49 → C · 57
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__ sink, eval()/exec(), __import__()
analyzed commit 4b69310 · analyzer v33 · 1d ago
skills & prompt files 15
- agent-rules LangeVC-skillweave-4b69310/AGENTS.md
- agent-rules LangeVC-skillweave-4b69310/CLAUDE.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-blueprint/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-council/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-design/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-discovery/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-launch/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-lifecycle/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-observe/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-post-release/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-promptchain-execute/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-promptchain-generate/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-promptchain-validate/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-releasechain/SKILL.md
- skill LangeVC-skillweave-4b69310/skills/skillweave-repo-health/SKILL.md
danger signals6
- dynamic code execution __import__ sink LangeVC-skillweave-4b69310/src/skillweave/studio/hooks/engine/chain.py :295
env={**dict(__import__("os").environ), **env}, - dynamic code execution eval()/exec() LangeVC-skillweave-4b69310/src/skillweave/studio/hooks/engine/condition.py :111
result = eval(compile(tree, "<condition>", "eval"), safe_ns) # noqa: S307 - dynamic code execution __import__() LangeVC-skillweave-4b69310/tests/gate_b06/dod_proof.py :141
__import__(mod) - dynamic code execution __import__() LangeVC-skillweave-4b69310/tests/gate_b06/whitelabel_proof.py :37
__import__(mod_name) - dynamic code execution __import__() LangeVC-skillweave-4b69310/tests/test_gnf_remaining.py :27
__import__(module_name, fromlist=["_"]) - dynamic code execution __import__ sink LangeVC-skillweave-4b69310/tests/unit/test_runner_adapter.py :75
assert result.pid != __import__("os").getpid()
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:LangeVC/skillweave/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of LangeVC.