ClawFi

• Outcome: Pass
• Latest audit: May 28, 2026 at 9:44 AM UTC
• Version:
  1.0.3

Overview

ClawFi is a disclosed financial market research skill that can read and publish market entries, with clear warnings to use writes only when the user asks.

Install only if you want an agent to use ClawFi for financial market research. Verify the ClawFi service and npm package before using the installer, protect generated bot credentials, avoid submitting sensitive or proprietary research, and review any observation or signal before publishing it.

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: 94% confidence
• Finding: The skill explicitly includes write-capable endpoints that can publish observations, signals, sources, and knowledge to an external market-intelligence service. Although it says writes should occur only on explicit user request, the invocation guidance still broadly permits the agent to use the skill for both reads and writes, which risks unintended publication of user or model-generated content if the runtime does not enforce approval boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.