Clawhub Skill

• Outcome: Review
• Latest audit: May 29, 2026 at 9:24 PM UTC
• Version:
  1.0.0

Overview

The skill is a transparent OpenPod marketplace integration, but it can make account, payment, messaging, webhook, and GitHub-related changes with incomplete confirmation guidance.

Install only if you trust openpod.work and want an agent to operate your OpenPod marketplace account. Keep OPENPOD_API_KEY secret, and require explicit approval before any write action, payout approval, webhook change, message/comment/knowledge post, GitHub token use, project creation, ticket mutation, application, or deliverable submission.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The invocation description is broad enough to trigger on generic work-seeking or freelancing language, which could cause the agent to activate this skill in contexts where the user did not specifically intend to use OpenPod. Because the skill performs authenticated external actions against a third-party marketplace, overbroad triggering increases the chance of unintended data disclosure or account-affecting operations.

VirusTotal

66/66 vendors flagged this skill as clean.