Local-first governance layer for Claude Code, built entirely on its native primitives — hooks, subagents, skills, MCP. Turns every session into a queryable, local SQLite record, then reads it back to predict your next dispatch, recall past incidents, attribute cost, and gate commits. The record is the product.
This grade was produced by analyzer v30 , 3 version s behind the one running now. Detectors added since have not been applied here, so it is not directly comparable with a server analyzed at the current version. A re-scan is queued.
- capability exposure inferred + 4
- recent drift inferred + 20
- tool safety inferred + 12
- 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.
graded 6m ago · see ecosystem CVEs →
- B · 25 → B · 33
- A · 0 → B · 25
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key · dynamic exec: new Function()
analyzed commit 4750108 · analyzer v30 · 2w ago
skills & prompt files 41
- agent-rules ek33450505-claude-agent-team-4750108/CLAUDE.md
- agent-rules ek33450505-claude-agent-team-4750108/commands/agents.md
- agent-rules ek33450505-claude-agent-team-4750108/plugin/commands/agents.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/agent-registry/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/briefing-writer/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/careful-mode/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/cast-audit/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/cast-conventions/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/deep-research/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/freeze-mode/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/git-activity/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/laconic/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/merge/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/orchestrate/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/plan/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/python-conventions/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/seo-checklist/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/ship/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/stack-reference/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/typescript-conventions/SKILL.md
- skill ek33450505-claude-agent-team-4750108/plugin/skills/wizard/SKILL.md
- agent-rules ek33450505-claude-agent-team-4750108/rules-core/agents.md
- skill ek33450505-claude-agent-team-4750108/skills-personal/project-catalog/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/agent-registry/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/briefing-writer/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/careful-mode/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/cast-audit/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/cast-conventions/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/deep-research/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/freeze-mode/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/git-activity/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/laconic/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/merge/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/orchestrate/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/plan/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/python-conventions/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/seo-checklist/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/ship/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/stack-reference/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/typescript-conventions/SKILL.md
- skill ek33450505-claude-agent-team-4750108/skills/wizard/SKILL.md
danger signals5
- dynamic code execution new Function() ek33450505-claude-agent-team-4750108/plugin/skills/deep-research/deep-research.verify.cjs :45
const makeRunner = (body) => new Function('agent', 'parallel', 'pipeline', 'log', 'phase', 'args', - dynamic code execution new Function() ek33450505-claude-agent-team-4750108/skills/deep-research/deep-research.verify.cjs :45
const makeRunner = (body) => new Function('agent', 'parallel', 'pipeline', 'log', 'phase', 'args', - committed secret Anthropic key ek33450505-claude-agent-team-4750108/evals/cases/security/security-hardcoded-api-key-unreported.yaml :25
sk-ant…(86 chars, redacted) - committed secret Anthropic key ek33450505-claude-agent-team-4750108/scripts/ci-pii-scan.sh :171
sk-ant…(44 chars, redacted) - committed secret Anthropic key ek33450505-claude-agent-team-4750108/tests/cast-subagent-stop-hook-redaction.bats :116
sk-ant…(43 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:ek33450505/claude-agent-team/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 ek33450505.