Argos Product Research

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 9:07 AM UTC
• Version: 1.0.0

Overview

This skill is a straightforward Argos product research helper, with no embedded code or hidden behavior found, though its install command and optional local caching deserve normal user caution.

Install only from a trusted registry and avoid running the npx command with administrator privileges. If possible, pin the installer version or use a reviewed local install path. Be aware the skill may cache product data locally if enabled, although the example config disables caching by default.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: README.md:13

Finding

Unpinned Package Execution During Installation

Content

View full analysis

Vulnerability Details

File Location: README.md, lines 13-16
Vulnerability Type: Supply-chain exposure through unpinned package execution
Risk Level: Medium

Vulnerable Code Snippet:

markdown

### Via ClawHub
```bash
npx skills add argos-product-research -g -y

text

### Technical Analysis

The documented installation command invokes the `skills` package through `npx` without specifying an exact package version or verifying its integrity. If the package is not already available in the local cache, `npx` may retrieve the package selected by the configured npm registry at installation time. Consequently, the code executed can differ from the code that was reviewed.

The `-y` option suppresses interactive confirmation, reducing the opportunity for users to inspect which package and version will execute. The `-g` option requests global skill installation, increasing the persistence and scope of any malicious skill content installed through the command.

Exploitation depends on compromise or malicious control of the referenced npm package, its maintainer account, a transitive dependency, the configured package registry, or the package-resolution environment. The repository itself does not contain an embedded malicious payload, and the audit found no evidence that the current `skills` package is malicious.

### Attack Path

1. An attacker compromises the npm package, a maintainer account, a transitive dependency, or a registry used to resolve the unversioned `skills` package.
2. The attacker publishes a malicious release that is selected by the unpinned `npx skills` invocation.
3. A user follows the README and executes:
   `npx skills add argos-product-research -g -y`
4. `npx` downloads and runs the attacker-controlled package version without an explicit version constraint and with confirmation suppressed.
5. Malicious package lifecycle or runtime code executes with the privileges of the invoking user.
...[truncated 845 chars]

Remediation

View remediation

Remediation Suggestions

• Pin the installer package to a reviewed exact version, for example:

  bash

  npx --yes skills@<reviewed-exact-version> add argos-product-research -g
  

• Do not use a floating tag such as latest; update the pinned version only after reviewing the release and its dependency changes.
• Prefer a package manager lockfile and a reproducible local installation workflow where feasible.
• Publish and verify package integrity information, provenance attestations, and cryptographic signatures.
• Remove -y from the recommended command when unattended installation is unnecessary so users can review package-resolution prompts.
• Avoid global installation by default. Document a user-local or project-local installation method and explain when global installation is required.
• Advise users not to run the installation command with administrator or root privileges.
• Use a trusted registry and consider constraining registry configuration explicitly for automated environments.

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 91% confidence

Finding

The README instructs users to install the skill via npx skills add argos-product-research -g -y without pinning the version of the package being executed. This creates a supply-chain risk because npx will fetch and run the latest published package, so a compromised or malicious update to skills could execute arbitrary code on the user's system during installation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The skill explicitly permits use of Read/Write to cache product data locally but does not disclose this behavior or define limits on what may be stored. Even if the primary data is public product information, local caching can still retain user queries, derived preferences, or scraped content longer than expected, creating avoidable privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.