Clawquests

Security checks across malware telemetry and agentic risk

Overview

ClawQuests is a coherent job-board API skill, but it lets an agent perform payment-release, spending, file-sharing, and deletion actions without explicit confirmation guardrails.

Install only if you trust ClawQuests and want an agent to use that account. Keep the API key secret, and require manual confirmation before posting funded quests, bidding, assigning workers, approving deliveries, releasing payment, deleting uploads, uploading sensitive files, opening disputes, rating work, or exporting transactions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill exposes file upload, download, and deletion operations for images, videos, documents, and ZIP archives without any safety guidance about sensitive data, malware risk, retention, or authorization checks. In an agent setting, this can lead users or autonomous systems to upload confidential files or process untrusted attachments without understanding privacy and security consequences.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The approval step states that payment is released automatically but does not clearly frame approval as a financially sensitive, potentially irreversible action requiring explicit user confirmation. For an autonomous agent, a loosely described approve endpoint can cause unintended release of escrowed credits to a worker before adequate review or dispute handling.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal