Prism-inspired multi-agent orchestration framework built on LangGraph. Security-first, provider-agnostic, composable.
- capability exposure inferred + 35
- recent drift inferred + 12
- tool safety inferred + 5
- trust mitigators mixed − 3
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 6m ago · see ecosystem CVEs →
- B · 32 → C · 49
- A · 0 → B · 32
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__(), __import__ sink
analyzed commit 9f0e37f · analyzer v28 · 1d ago
skills & prompt files 2
danger signals5
- dynamic code execution __import__() prismal-ai-prismal-9f0e37f/tests/unit/agents/subgraphs/skynet/test_builder_plus.py :59
real_supervisor = __import__( - dynamic code execution __import__ sink prismal-ai-prismal-9f0e37f/tests/unit/core/config_source/test_no_import_mutation.py :24
env = {"LIGHTAGENT_FOO": "bar", "PATH": __import__("os").environ.get("PATH", "")} - suspicious endpoint api.telegram.org prismal-ai-prismal-9f0e37f/prismal/scheduler/heartbeat_delivery.py :22
_TELEGRAM_API = "https://api.telegram.org" - suspicious endpoint api.telegram.org prismal-ai-prismal-9f0e37f/prismal/scheduler/notifier.py :22
_TELEGRAM_API = "https://api.telegram.org" - suspicious endpoint discord.com prismal-ai-prismal-9f0e37f/tests/unit/scheduler/test_heartbeat_delivery.py :68
webhook_url = "https://discord.com/api/webhooks/123/abc"
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:prismal-ai/prismal/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 prismal-ai.