MCP Observatory
github re-analysis due

Conalh/agent-gov-demo

github

Sandbox repo for the agent-gov suite — a rogue PR that trips ScopeTrail, PolicyMesh, CapabilityEcho, TaskBound, and SessionTrail at once.

maintainer
Conalh
license
MIT
first seen
2026-06-08
last seen
2026-06-08
releases · 30d
0
short id
risk 6/100 · heuristic grade
A minimal
  • capability exposureinferred+6

inferred

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 16m ago · see ecosystem CVEs →

risk trajectory 1 movements
  • A · 0 → A · 6
capability exposure grade factor +6
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety all quiet

No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.

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

analyzed commit 26db745 · analyzer v17 · 1d ago

skills & prompt files 2

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:Conalh/agent-gov-demo/badge.svg)](https://mcpobservatory.com/servers/github:Conalh/agent-gov-demo/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 Conalh.