ClawHub
Back to skill

Security audit

ViralQuery

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for using ViralQuery, but it asks users to run an unpinned npm CLI with an API key and treats mutable remote documentation as operational authority.

Review before installing. Use an environment or secret store for the API key, avoid running the unpinned `npx viralquery` command with a live key unless you trust the npm package and publisher, and prefer a pinned or manually verified setup path. Treat remote docs as reference only and keep API actions limited to your intended ViralQuery tenant/workspace.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)

T08 · Insecure Dependencies

Error
Location
SKILL.md:29
Finding

Unpinned Third-Party Package Execution with API Credential Access

Content
View full analysis
Remediation
View remediation
auth --url https://api.viralquery.com ``` 2. Publish and verify package integrity metadata, provenance, and the expected npm publisher before execution. Where possible, use a lockfile and a trusted registry configuration. 3. Prefer a direct, documented configuration mechanism that writes the configuration file locally without executing newly downloaded code. 4. Do not pass credentials through command-line arguments. Read the key from a protected environment variable, standard input, or an operating-system secret store within a previously installed and verified client. 5. Ensure configuration files are created with restrictive permissions and never emit the key to logs. 6. Document credential rotation and revocation procedures for users who may have run an untrusted package version. ]]>

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:10
Finding

Mutable Remote Documentation Is Trusted as Operational Authority

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: viralquery
description: Set up and use ViralQuery's protected HTTP API to build a private video inspiration feed for one app, website, or niche. Use when an agent needs to help obtain or configure a ViralQuery API key, verify authentication, create or update a research brief and rules, run and monitor a scroll, or retrieve tenant-scoped library, outlier, trend, and hook signals.
---

# ViralQuery

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

  • otherwise read apiKey and optional apiUrl from ~/.viralquery/config.json when present.

  1. If no key is configured, tell the user to open viralquery.com/#pricing, choose a plan, finish checkout, and save the key shown once. Never ask the user to paste the key into chat.

  2. Configure either of these supported forms:

    bash

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs use of npx viralquery without pinning an exact package version. That allows the executed package to change over time and increases supply-chain risk if a malicious or compromised version is published, especially because this command is used during authentication setup and may handle API credentials.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The default prompt triggers a broad sequence of sensitive actions: verifying API setup, configuring briefs and rules, running a scroll, and returning results, without stating when the skill should or should not activate. In an agent environment, this can cause over-broad invocation, unintended use of protected API credentials, or autonomous external actions based on weak user intent matching.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:27