MolTrust Protocol — AI Agent Trust Infrastructure
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 17
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 1w ago · see ecosystem CVEs →
- D · 67 → D · 72
- D · 64 → D · 67
- C · 56 → D · 64
- B · 32 → C · 56
- A · 0 → B · 32
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tool + source surface: private-data access + untrusted-content ingestion + network exfil (a leg is proven only in the analyzed source)
analyzed commit d6243e1 · analyzer v33 · 1m ago
skills & prompt files 1
- agent-rules MoltyCel-moltrust-api-d6243e1/CLAUDE.md
danger signals21
- suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/ai_review.py :724
f"https://api.telegram.org/bot{TG_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/ai_review_v2.py :286
f"https://api.telegram.org/bot{TG_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/herald.py :42
f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/herald_v3.py :133
f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/news_scout.py :329
url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage" - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/pr_monitor.py :142
url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage" - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/retention_cleanup.py :28
url = f"https://api.telegram.org/bot{TG_TOKEN}/sendMessage" - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/traffic_monitor.py :184
f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/agents/watchdog.py :92
f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/app/budget.py :407
f"https://api.telegram.org/bot{token}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/app/notify.py :104
r = requests.post(f"https://api.telegram.org/bot{token}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/monitor/poll_payments.py :93
_tg_url = "https://api.telegram.org/bot" + TELEGRAM_BOT_TOKEN + "/sendMessage" - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/scripts/auto_repair.py :71
url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage" - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/scripts/concept_review.py :224
f"https://api.telegram.org/bot{TG_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/scripts/discovery_snapshot.py :262
f"https://api.telegram.org/bot{tok}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/scripts/endpoint_probe.py :120
f"https://api.telegram.org/bot{TG_TOKEN}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/scripts/funnel_diff.py :93
req = urllib.request.Request(f"https://api.telegram.org/bot{token}/sendMessage", data=data) - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/scripts/telegram_hn_remind.py :25
f'https://api.telegram.org/bot{token}/sendMessage', - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/scripts/threadwatch.py :238
f"https://api.telegram.org/bot{token}/sendMessage", - suspicious endpoint api.telegram.org MoltyCel-moltrust-api-d6243e1/workers/content_scout/telegram.py :17
httpx.post(f"https://api.telegram.org/bot{token}/sendMessage", - committed secret Anthropic key MoltyCel-moltrust-api-d6243e1/pentest.sh :38
sk-ant…(38 chars, redacted)
- recent drift +20 capability drift →
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 MoltyCel.