APX — unified CLI + daemon for the Agent Project Context (APC) standard.
- capability exposure inferred + 35
- recent drift inferred + 12
- inherited (deps) attested + 15
- tool safety inferred + 5
- supply-chain attested + 6
- trust mitigators mixed − 3
attested 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 10m ago · see ecosystem CVEs →
- B · 18 → D · 70
No known CVEs for this server.
inherited (deps) · grade factor +15
- medium dangerous code
dynamic exec: new Function()
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (package/src/core/agent/tools/regis
analyzed v1.74.0 · analyzer v28 · 2d ago
skills & prompt files 22
- skill package/skills/apc-context/SKILL.md
- skill package/skills/apx-mcp/SKILL.md
- skill package/skills/apx/SKILL.md
- skill package/src/core/runtime-skills/apc-context/SKILL.md
- skill package/src/core/runtime-skills/apx-agency-agents/SKILL.md
- skill package/src/core/runtime-skills/apx-agent/SKILL.md
- skill package/src/core/runtime-skills/apx-mcp-builder/SKILL.md
- skill package/src/core/runtime-skills/apx-mcp/SKILL.md
- skill package/src/core/runtime-skills/apx-project/SKILL.md
- skill package/src/core/runtime-skills/apx-routine/SKILL.md
- skill package/src/core/runtime-skills/apx-runtime/SKILL.md
- skill package/src/core/runtime-skills/apx-sessions/SKILL.md
- skill package/src/core/runtime-skills/apx-skill-builder/SKILL.md
- skill package/src/core/runtime-skills/apx-task/SKILL.md
- skill package/src/core/runtime-skills/apx-telegram/SKILL.md
- skill package/src/core/runtime-skills/apx-voice/SKILL.md
- skill package/src/core/runtime-skills/apx/SKILL.md
- skill package/src/core/runtime-skills/claude-code/SKILL.md
- skill package/src/core/runtime-skills/codex-cli/SKILL.md
- skill package/src/core/runtime-skills/opencode-cli/SKILL.md
- skill package/src/core/runtime-skills/openrouter/SKILL.md
- skill package/src/skills/apc-context/SKILL.md
danger signals4
- dynamic code execution new Function() package/src/core/http-tools/browser.js :402
result = await page.evaluate(new Function(code)); - suspicious endpoint api.telegram.org package/src/core/channels/telegram/media.js :12
export const API_BASE = "https://api.telegram.org"; - suspicious endpoint api.telegram.org package/src/host/daemon/wakeup.js :54
const url = `https://api.telegram.org/bot${token}/sendMessage`; - suspicious endpoint t.me package/src/interfaces/cli/commands/setup.js :193
console.log(di(" Create a bot at https://t.me/BotFather → get the token."));
- recent drift +12 capability drift →
- supply-chain +6 supply-chain hub →
[](https://mcpobservatory.com/servers/npm:@agentprojectcontext/apx/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 tecnomanu.