Talos — deterministic runtime firewall SDK for AI agents. Prompt-injection screening, deny-by-default tool-call gating (shell, filesystem, network, wallet), and secret-leak scanning. Model-agnostic, zero dependencies, probe-tested. The runtime guardian counterpart to Nullsec-S1.
- capability exposureinferred+22
- recent driftinferred+12
- tool safetyinferred+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.
graded 2m ago · see ecosystem CVEs →
- A · 0 → C · 46
No known CVEs for this server.
- highdangerous code
committed secret: GitHub token
analyzed commit 873333f · analyzer v20 · 21h ago
danger signals2
- suspicious endpoint169.254.169.254 (cloud metadata)trynullsec-nullsec-talos-873333f/nullsec_talos/probes.py:120
"args": {"url": "http://169.254.169.254/latest/meta-data/iam/"}, - committed secretGitHub tokentrynullsec-nullsec-talos-873333f/nullsec_talos/probes.py:187
ghp_01…(42 chars, redacted)
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:trynullsec/nullsec-talos/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 trynullsec.