The agentic harness for AI coding agents — work cycles, bounded RAG context, persistent memory, guardrails, and performance evals.
- capability exposure inferred + 35
- recent drift inferred + 20
- inherited (deps) attested + 15
- tool safety inferred + 12
- trust mitigators mixed − 14
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 40s ago · see ecosystem CVEs →
- C · 56 → D · 68
- D · 61 → C · 56
- C · 56 → D · 61
- D · 61 → C · 56
- C · 56 → D · 61
- C · 57 → C · 56
- C · 49 → C · 57
No known CVEs for this server.
inherited (deps) · grade factor +15
- high dangerous code
dynamic exec: eval(), new Function() · 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. (prjct-app-cli-08a1aac/core/command
analyzed v3.78.1 · analyzer v28 · 2d ago
skills & prompt files 2
danger signals2
- dynamic code execution eval() prjct-app-cli-08a1aac/core/commands/eval.ts :33
async eval( - dynamic code execution new Function() prjct-app-cli-08a1aac/scripts/build.js :229
new Function('module', 'exports', 'require', result.outputFiles[0].text)(
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:prjct-app/cli/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 prjct-app.