Declarative runtime, operations, and evaluation platform for multi-channel AI agents
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
inferred
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 · 59 → D · 67
No known CVEs for this server.
- high dangerous code
committed secret: GitHub fine-grained PAT · dynamic exec: unsafe yaml.load()
analyzed commit a602346 · analyzer v33 · 1d ago
skills & prompt files 18
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/00-global.mdc
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/10-architecture.mdc
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/20-botspec.mdc
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/30-middleware.mdc
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/40-agent.mdc
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/50-external-tools.mdc
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/60-deploy-and-tests.mdc
- agent-rules Ling-ye-AgentStrata-a602346/.cursor/rules/70-frontend-design.mdc
- skill Ling-ye-AgentStrata-a602346/.cursor/skills/debug-chatcopilot-bot/SKILL.md
- agent-rules Ling-ye-AgentStrata-a602346/AGENTS.md
- prompt-file Ling-ye-AgentStrata-a602346/bots/_template/prompts/identity.md
- prompt-file Ling-ye-AgentStrata-a602346/bots/_template/prompts/refusal-style.md
- prompt-file Ling-ye-AgentStrata-a602346/bots/_template/prompts/response-style.md
- prompt-file Ling-ye-AgentStrata-a602346/bots/lingye-copilot-qq/prompts/identity.md
- prompt-file Ling-ye-AgentStrata-a602346/bots/lingye-copilot-qq/prompts/refusal-style.md
- prompt-file Ling-ye-AgentStrata-a602346/bots/lingye-copilot-qq/prompts/response-style.md
- skill Ling-ye-AgentStrata-a602346/bots/lingye-copilot-qq/skills/ai-career-intelligence/SKILL.md
- skill Ling-ye-AgentStrata-a602346/bots/lingye-copilot-qq/skills/ai-jd-analysis/SKILL.md
danger signals4
- dynamic code execution unsafe yaml.load() Ling-ye-AgentStrata-a602346/src/chatcopilot/core/wiki/store.py :474
metadata = yaml.load(normalized[4:end]) or {} - dynamic code execution unsafe yaml.load() Ling-ye-AgentStrata-a602346/src/chatcopilot/evals/manifest.py :740
raw = yaml.load(text) - dynamic code execution unsafe yaml.load() Ling-ye-AgentStrata-a602346/tests/unit/test_agentstrata_capability_suite_data.py :71
value = yaml.load(text) - committed secret GitHub fine-grained PAT Ling-ye-AgentStrata-a602346/tests/unit/test_code_task_delivery.py :61
github…(33 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:Ling-ye/AgentStrata/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 Ling-ye.