Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.
- capability exposure inferred + 35
- tool safety inferred + 12
- trust mitigators mixed − 8
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 8m ago · see ecosystem CVEs →
- B · 27 → C · 39
- A · 14 → B · 27
No known CVEs for this server.
- high dangerous code
suspicious bundled script in 2 file(s) · obfuscated payload: dynamic require()/import()
- medium dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (tokencanopy-e2a-e2e26fc/plugins/e2
analyzed commit b25046c · analyzer v28 · 3d ago
skills & prompt files 8
- agent-rules tokencanopy-e2a-b25046c/AGENTS.md
- agent-rules tokencanopy-e2a-b25046c/CLAUDE.md
- skill tokencanopy-e2a-b25046c/plugins/e2a/skills/agentify/SKILL.md
- skill tokencanopy-e2a-b25046c/plugins/e2a/skills/agentify/templates/runtime-skill/SKILL.md
- prompt-file tokencanopy-e2a-b25046c/plugins/e2a/skills/agentify/test/fixtures/harness/prompts/triage.txt
- skill tokencanopy-e2a-b25046c/plugins/e2a/skills/autopilot/SKILL.md
- skill tokencanopy-e2a-b25046c/plugins/e2a/skills/e2a/SKILL.md
- skill tokencanopy-e2a-b25046c/plugins/e2a/skills/tether/SKILL.md
danger signals2
- suspicious bundled script suspicious bundled script tokencanopy-e2a-b25046c/plugins/e2a/skills/autopilot/lib.sh :22
eval "$(python3 -c 'import json,shlex,os - suspicious bundled script suspicious bundled script tokencanopy-e2a-b25046c/plugins/e2a/skills/tether/lib.sh :27
eval "$(python3 -c 'import json,shlex,os
[](https://mcpobservatory.com/servers/github:Mnexa-AI/e2a/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 Mnexa-AI.