Agent-agnostic context engine that gives AI coding agents continuous memory across sessions, tools, and machines.
- vulnerabilities attested + 18
- capability exposure inferred + 35
- tool safety inferred + 5
attested 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 2h ago · see ecosystem CVEs →
- C · 53 → C · 58
- C · 35 → C · 53
- B · 26 → C · 35
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit cb7dd56 · analyzer v33 · 2h ago
skills & prompt files 1
- agent-rules sammyjdev-axon-cb7dd56/CLAUDE.md
danger signals8
- dynamic code execution eval()/exec() sammyjdev-axon-cb7dd56/tests/http/test_activity_dashboard_xss.py :262
eval(PAGE_JS); - suspicious endpoint 169.254.169.254 (cloud metadata) sammyjdev-axon-cb7dd56/tests/expansion/test_transport_ssrf.py :24
await UrllibSourceTransport().fetch("http://169.254.169.254/latest/meta-data/") - suspicious endpoint 93.184.216.34 sammyjdev-axon-cb7dd56/tests/expansion/test_url_safety.py :26
check_url_safety("http://93.184.216.34/") - suspicious endpoint 169.254.169.254 (cloud metadata) sammyjdev-axon-cb7dd56/tests/expansion/test_url_safety.py :34
"http://169.254.169.254/", - suspicious endpoint 100.100.100.200 (cloud metadata) sammyjdev-axon-cb7dd56/tests/expansion/test_url_safety.py :39
"http://100.100.100.200/", # CGNAT / Shared Address Space, RFC 6598 - suspicious endpoint 192.0.0.8 sammyjdev-axon-cb7dd56/tests/expansion/test_url_safety_special_use.py :11
"http://192.0.0.8/", # IETF protocol assignment (used for NAT64/DNS64 discovery) - suspicious endpoint 192.0.0.170 sammyjdev-axon-cb7dd56/tests/expansion/test_url_safety_special_use.py :12
"http://192.0.0.170/", # NAT64 well-known prefix address, same /24 - suspicious endpoint 192.88.99.2 sammyjdev-axon-cb7dd56/tests/expansion/test_url_safety_special_use.py :23
"http://192.88.99.2/", # 6to4 relay anycast (RFC 7526), is_global=True on 3.11
[](https://mcpobservatory.com/servers/github:sammyjdev/axon/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 sammyjdev.