npm analyzed 6.1.0

event4u-app/agent-config

v6.1.0

npm

Universal AI Agent OS — audited skills, governance rules, replayable state. One contract, every host agent.

maintainer: event4u-app
license: MIT
first seen: 2026-06-02
last seen: 2026-06-17
releases · 30d: 64
short id

risk 70/100 · heuristic grade

D high

capability exposureinferred+35
recent driftinferred+20
tool safetyinferred+24
trust mitigatorsmixed−9

inferredmixed

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 8m ago · see ecosystem CVEs →

risk trajectory 4 movements

8h agoC · 45 → D · 70
20h agoC · 58 → C · 45
5d agoD · 70 → C · 58
6d agoC · 45 → D · 70

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

highdangerous code
dynamic exec: eval()/exec()
highhidden prompt content
2 file(s) with hidden prompt content: event4u-app-agent-config-22bc763/dist/agent-src/templates/skill.md (hidden-directive), event4u-app-agent-config-22bc763/src/agent-src/templat…

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v6.1.0 · analyzer v18 · 8h ago

skills & prompt files 192

⚠ hidden: skill: hidden-directiveevent4u-app-agent-config-22bc763/dist/agent-src/templates/skill.md:61DESCRIPTION RULES (delete this comment when done): - Start with "Use when..." — this is a TRIGGER, not a summary - Include 2-3 phrases users actually say: "create a DTO", "add column", "fix tests"
⚠ hidden: skill: hidden-directiveevent4u-app-agent-config-22bc763/src/agent-src/templates/skill.md:61DESCRIPTION RULES (delete this comment when done): - Start with "Use when..." — this is a TRIGGER, not a summary - Include 2-3 phrases users actually say: "create a DTO", "add column", "fix tests"

danger signals1

dynamic code executioneval()/exec()event4u-app-agent-config-22bc763/src/scripts/check_trigger_evals.py:19model-based routing eval (`skill_trigger_eval.py`) is separate and

other grade factors evidence elsewhere

recent drift+20 capability drift →

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:@event4u/agent-config/badge.svg)](https://mcpobservatory.com/servers/npm:@event4u/agent-config/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 event4u-app.

event4u-app/agent-config

skills & prompt files 192

danger signals1

Navigate

Stream

Display