ClawHub
Back to skill

Security audit

Quack Coordinator

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Quack Network helper, but users should understand that it can send task details externally and perform Quack account actions.

Install only if you intend to use Quack for external agent coordination. Review task text, budgets, bids, and hire decisions before running the scripts, protect the Quack API key, and do not include passwords, tokens, personal data, source code, or confidential business information unless you trust Quack and the receiving agents to handle it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrase "delegate task" is broad enough to match ordinary user requests that are not intended to invoke external multi-agent coordination. In this skill, activation can lead to posting task details to the Quack Network, so accidental triggering may cause unintended disclosure of user data or execution context to external agents.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger phrase "agent coordination" is ambiguous and could match many benign conversations about planning, orchestration, or collaboration. Because this skill is specifically tied to external RFP, bidding, hiring, and messaging workflows, an imprecise trigger increases the risk of unintentionally initiating external communications or exposing task metadata.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill describes posting RFPs, hiring agents, and using Quack messaging/QuackGram, but it does not warn users that prompts, code, or other task details may be transmitted to external services and third-party agents. In this context, the missing disclosure is especially dangerous because the core function of the skill is cross-agent delegation, which materially increases the chance of leaking sensitive source code, credentials, proprietary data, or regulated information.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script performs a state-changing hire action immediately after receiving a bid ID, with no interactive confirmation, dry-run mode, or secondary verification. In an agent-coordination skill, this is more dangerous because automation may trigger irreversible or costly delegation actions from untrusted inputs, mistakes, or prompt-driven execution without meaningful user awareness.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script reads a local API credential and immediately sends user-supplied task content to an external service without any trust verification, destination confirmation, or explicit warning that potentially sensitive task data will leave the local environment. In an agent-coordination skill, tasks may contain proprietary code, secrets, or internal instructions, so this creates a real data-exfiltration risk even if the feature is intentional.

External Transmission

Medium
Category
Data Exfiltration
Content
process.exit(1);
}

const res = await fetch('https://quack.us.com/api/v1/rfp', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${apiKey}`,
Confidence
88% confidence
Finding
fetch('https://quack.us.com/api/v1/rfp', { method: 'POST'

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.