npm JavaScript analyzed 2026.7.24

aiwg

v2026.7.24

Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo

maintainer: —
license: MIT
first seen: 2026-06-02
last seen: 2026-07-29
releases · 30d: 20
short id

risk 83/100 · heuristic grade

E critical

capability exposure inferred + 35
recent drift inferred + 20
inherited (deps) attested + 15
tool safety inferred + 12
abandonment inferred + 10
trust mitigators mixed − 9

attested 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 17s ago · see ecosystem CVEs →

risk trajectory 5 movements

3d ago D · 63 → E · 83
1w ago D · 60 → D · 63
3w ago D · 68 → D · 60
4w ago D · 60 → D · 68
5w ago D · 72 → D · 60

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 0 CVEs

No known CVEs for this server.

inherited (deps) · grade factor +15

inherited via dependencies 3

HIGH

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse via @modelcontextprotocol/sdk · 1 hop CVE-2026-25536 fixed in 1.26.0

HIGH

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability via @modelcontextprotocol/sdk · 1 hop CVE-2026-0621 fixed in 1.25.2

HIGH

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default via @modelcontextprotocol/sdk · 1 hop CVE-2025-66414 fixed in 1.24.0

tool safety 1 findings · grade factor +12

high dangerous code

dynamic exec: indirect eval · suspicious bundled script in 2 file(s) · obfuscated payload: dynamic require()/import()

skills & danger signals npm-tarball

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

analyzed v2026.7.24 · analyzer v28 · 2d ago

skills & prompt files 183

danger signals4

dynamic code execution indirect eval package/dist/src/cli/log.js :124 const require = (0, eval)('require');
suspicious endpoint api.telegram.org package/tools/messaging/adapters/telegram.mjs :100 this.#apiBase = `https://api.telegram.org/bot${this.#botToken}`;
suspicious bundled script suspicious bundled script package/agentic/code/addons/aiwg-utils/skills/steward-prep-delivery/find-duplicates.sh :95 eval "$(python3 -c "
suspicious bundled script suspicious bundled script package/agentic/code/plugins/utils/skills/steward-prep-delivery/find-duplicates.sh :95 eval "$(python3 -c "

other grade factors evidence elsewhere

recent drift +20 capability drift →
abandonment +10 abandonment hub →

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:aiwg/badge.svg)](https://mcpobservatory.com/servers/npm:aiwg/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.

aiwg

skills & prompt files 183

danger signals4

Navigate

Stream

Features

Display