Личный ассистент-агент (Ева) на eve + Ollama Cloud (DeepSeek-V4-Pro): личность, скиллы, субагенты, Telegram, cron
- capability exposure inferred + 28
- recent drift inferred + 20
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 5d ago · see ecosystem CVEs →
- D · 60 → C · 48
- D · 72 → D · 60
- C · 44 → D · 72
- C · 36 → C · 44
- C · 35 → C · 36
- A · 0 → C · 35
No known CVEs for this server.
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
analyzed commit f5bb315 · analyzer v33 · 3d ago
skills & prompt files 7
- skill smixs-iva-agent-f5bb315/agent/skills/agent-browser/SKILL.md
- skill smixs-iva-agent-f5bb315/agent/skills/rich-post/SKILL.md
- skill smixs-iva-agent-f5bb315/agent/skills/security-defense/SKILL.md
- skill smixs-iva-agent-f5bb315/agent/skills/telegram-userbot/SKILL.md
- skill smixs-iva-agent-f5bb315/agent/skills/update-recovery/SKILL.md
- skill smixs-iva-agent-f5bb315/scripts/autograph/docs/SKILL.md
- skill smixs-iva-agent-f5bb315/scripts/memory/instructions/memory-processor/SKILL.md
danger signals1
- suspicious endpoint api.telegram.org smixs-iva-agent-f5bb315/services/telegram-userbot/onboarding.py :77
f"https://api.telegram.org/bot{token}/sendPhoto",
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:smixs/eve-assistant/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 smixs.