Build agent applications with typed chat, tools, sandboxes, integrations, billing, and evaluation.
- capability exposure inferred + 35
- trust mitigators mixed − 9
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 1m ago · see ecosystem CVEs →
- A · 9 → B · 26
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed v0.45.12 · analyzer v28 · 2h ago
skills & prompt files 7
- skill package/.claude/skills/eval-architect/SKILL.md
- skill package/.claude/skills/eval-bootstrap/SKILL.md
- skill package/.claude/skills/eval-campaign/SKILL.md
- skill package/.claude/skills/improve-conductor/SKILL.md
- skill package/.claude/skills/measurement-validation/SKILL.md
- skill package/.claude/skills/skill-evolution/SKILL.md
- skill package/.claude/skills/surface-evolution/SKILL.md
[](https://mcpobservatory.com/servers/npm:@tangle-network/agent-app/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 drewstone.