github Python analyzed a29851e deep scan · partial (289/3,695 files)

als-apg/osprey

github

An agentic interface and safety harness for safety-critical control systems

maintainer
als-apg
licence
BSD-3-Clause
first seen
2026-07-09
last seen
2026-09-10
releases · 30d
1
short id
risk 66/100 · heuristic grade
D high inferred analyzer v33 (current)
  • capability exposure inferred + 35
  • recent drift inferred + 20
  • tool safety inferred + 19
  • trust mitigators mixed − 8

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.

grade last moved 3d ago · see ecosystem CVEs →

risk trajectory 4 movements
  • D · 61 D · 66
  • D · 66 D · 61
  • C · 59 D · 66
  • C · 51 C · 59
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 3 findings · grade factor +19
  1. high dangerous code

    committed secret: Anthropic key · dynamic exec: unsafe yaml.load(), __import__(), eval()/exec(), __import__ sink

  2. medium tool shadowing execute

    tool "execute" shadows a verified server's tool

    shadows claytono/go-unifi-mcp

  3. low exfiltration combo

    sensitive read and network capabilities split across this server's tools

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit a29851e · analyzer v33 · 6h ago

skills & prompt files 16

danger signals32

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:als-apg/osprey/badge.svg)](https://mcpobservatory.com/servers/github:als-apg/osprey/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 als-apg.