Raccoon Data Analysis

• Outcome: Review
• Latest audit: May 28, 2026, 7:19 AM
• Version:
  1.0.3

Overview

The skill mostly matches its remote data-analysis purpose, but it saves and opens provider-controlled result files too broadly and exposes part of the API token in one command.

Review before installing. Use it only with files you are allowed to send to the configured RACCOON_API_HOST, verify that host is trusted and HTTPS, avoid running auth-check where logs may be captured, and prefer --no-open until artifact filenames are sanitized and automatic opening is opt-in.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

system = platform.system()
    try:
        if system == "Darwin":
            subprocess.run(["open", path], check=False)
        elif system == "Linux":
            subprocess.run(["xdg-open", path], check=False)
    except Exception:

• Confidence: 91% confidence
• Finding: subprocess.run(["open", path], check=False)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

if system == "Darwin":
            subprocess.run(["open", path], check=False)
        elif system == "Linux":
            subprocess.run(["xdg-open", path], check=False)
    except Exception:
        pass

• Confidence: 91% confidence
• Finding: subprocess.run(["xdg-open", path], check=False)

Context-Inappropriate Capability

Medium

• Confidence: 93% confidence
• Finding: The skill goes beyond data-analysis/session management by automatically launching local files after download. In this context that is more dangerous because users expect analysis, not local application invocation; a malicious or malformed artifact could trigger risky file handlers or unwanted browsing activity.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: User-supplied files are uploaded to a remote API service with no explicit warning or consent prompt at the point of transfer. In a data-analysis skill this is especially relevant because users may provide sensitive spreadsheets or documents and may not realize the content leaves the local environment.

Missing User Warnings

Low

• Confidence: 82% confidence
• Finding: The tool writes remote-generated artifacts to local disk by default without a strong user-facing warning. While lower severity than remote upload, this can create unexpected local files and persistence of potentially sensitive or unsafe content.

VirusTotal

VirusTotal findings are pending for this skill version.