ClawHub

jf-open-pro-video-masking

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This skill does what it claims, but it controls a camera and can stop recording while using credentials and an unrestricted API endpoint, so users should review it carefully before installing.

Install only if you trust the publisher and understand that this can move your camera and stop or resume recording. Use a fixed trusted JFTech API host, avoid setting JF_ENDPOINT to anything else, protect the JF_* credentials, and require explicit confirmation before enable, disable, or toggle actions.

SkillSpector (4)

By NVIDIA

Tainted flow: 'url' from os.getenv (line 56, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Content
]
    }
    
    response = requests.post(url, headers=headers, json=body, timeout=30)
    result = response.json()
    
    if result.get("code") != 2000:
Confidence
93% confidence
Finding
response = requests.post(url, headers=headers, json=body, timeout=30)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documentation requires multiple sensitive environment variables and explicitly invokes a Python script that performs authenticated API calls over the network, yet no permissions are declared. This creates a transparency and governance gap: users or the platform may not be properly informed that the skill reads secrets and can issue device-control requests affecting camera behavior and recording state.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger phrase “隐私模式” is broad and likely to overlap with ordinary user speech, increasing the chance of accidental activation. In this skill, accidental activation is security-relevant because it can move the camera, disable preview, and stop recording, potentially creating unintended surveillance blind spots.

Vague Triggers

Low
Confidence
76% confidence
Finding
The trigger list does not define clear scope, context, or exclusion rules, so ambiguous utterances may still activate the skill unintentionally. While this is primarily a safety/usability issue, in this context it can still affect privacy and monitoring availability by changing camera masking state without clear user intent.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal