Loading npm security reports…

@quotient-forecasting/cassie-skill@0.3.0: AI-agent | LPM Firewall

registry / @quotient-forecasting/cassie-skill / 0.3.0

@quotient-forecasting/cassie-skill@0.3.0

Agent Skill operator manual and policy files for Cassie

AI Security Review

scanned 1mo ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. npm installation automatically modifies global skill directories for two AI coding-agent platforms. It installs a trading-operator skill that can influence later agent sessions.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

npm postinstall

Impact

A package install can add behavior-bearing trading instructions to Codex-style and Claude agent environments without an explicit setup command.

Mechanism

automatic overwrite of global AI-agent skill files

Policy narrative

Installing the package invokes install.mjs automatically. The installer creates and overwrites cassie skill files under global .agents and .claude skill roots. Those files are intended to be discovered by coding agents and instruct them how to fund, deploy, and trade through the Cassie CLI. This is an unconsented install-time mutation of foreign AI-agent control surfaces.

AI rationale

The package has no observed exfiltration or remote payload behavior, but its postinstall hook persistently modifies broad AI-agent skill locations. That concrete lifecycle control-surface mutation meets the publish-block policy.

Evidence

package.jsoninstall.mjsSKILL.md~/.agents/skills/cassie/SKILL.md~/.agents/skills/cassie/thesis~/.claude/skills/cassie/SKILL.md~/.claude/skills/cassie/thesis

Decision evidence

Source & flagged code

8 flagged · loading source

package.jsonView file

•scripts.postinstall = node install.mjs

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 1

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

package.jsonView on unpkg

36"scripts": { "postinstall": "node install.mjs" }

High

Ai Review Evidence

The manifest automatically runs the installer after npm installation.

package.jsonView on unpkg · L36

•scripts.postinstall = node install.mjs

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

install.mjsView file

3L4: import { cpSync, existsSync, mkdirSync } from "node:fs"; L5: import { homedir } from "node:os"; ... L12: function defaultRoots() { L13: return [join(homedir(), ".agents", "skills"), join(homedir(), ".claude", "skills")]; L14: } ... L27: const destination = join(root, "cassie"); L28: mkdirSync(destination, { recursive: true }); L29: cpSync(join(packageDir, "SKILL.md"), join(destination, "SKILL.md"), { force: true }); L30: cpSync(join(packageDir, "thesis"), join(destination, "thesis"), { recursive: true, force: true }); L31: installed.push(destination);

Critical

Ai Agent Control Hijack

Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.

install.mjsView on unpkg · L3

•Runtime or CLI code links a write operation to an explicit external AI-agent control path: import { cpsync, existssync, mkdirsync } from "node:fs"; import { homedir } from "node:os"; import { dirname, join, resolve } from "node:path"; import { fileurltopath } from "node:url"; const packagedir = dirname(fileurltopath(import.meta.url)); const workspaceroot = resolve(packagedir, "../.."); function defaultroots() { return [join(homedir(), ".agents", "skills"), join(homedir(), ".claude", "skills")]; } export function installcassieskill(options = {}) { const override = process.env.cassie_skills_dir?.trim(); if (!options.force && process.env.cassie_skip_skill_install === "1") return [];

High

External Ai Agent Control Surface Mutation

Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.

install.mjsView on unpkg

12function defaultRoots() { return [join(homedir(), ".agents", "skills"), join(homedir(), ".claude", "skills")]; }