github Python analyzed 0afd305

dsivov/cohermes

github

A team of AI coding agents that share one brain — a Hermes extension whose per-user memory becomes a shared, governed Context Graph.

maintainer
dsivov
license
MIT
first seen
2026-07-20
last seen
2026-07-22
releases · 30d
0
short id
risk 79/100 · heuristic grade
D high
  • capability exposure inferred + 35
  • recent drift inferred + 20
  • tool safety inferred + 24

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 54s ago · see ecosystem CVEs →

risk trajectory 1 movements
  • D · 71 D · 79
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 2 findings · grade factor +24
  1. high dangerous code

    committed secret: Anthropic key, Slack app token, OpenAI key, Slack token · dynamic exec: unsafe yaml.load(), __import__(), pickle.loads(), eval()/exec(), __import__ sink · suspic…

  2. high hidden prompt content

    2 file(s) with hidden prompt content: dsivov-cohermes-0afd305/skills/github/github-pr-workflow/SKILL.md (skill-exfil), dsivov-cohermes-0afd305/skills/productivity/airtable/SKILL.m…

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

analyzed commit 0afd305 · analyzer v28 · 3d ago

skills & prompt files 166

danger signals77

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