ClawHub

Image Edit Skill

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal image-processing skill with privacy and dependency hygiene caveats, not evidence of malicious or deceptive behavior.

Install only if you are comfortable with the skill processing local image files. Review EXIF/metadata before exporting or sharing it, avoid preserving EXIF unless needed, write batch outputs to a separate directory, and prefer a version that pins current patched dependencies and removes openpyxl if spreadsheet support is not required.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The declared purpose of this skill is Pillow-based image processing, but the dependency list also includes openpyxl, a spreadsheet library unrelated to that stated scope. Unnecessary capabilities expand the attack surface, increase supply-chain risk, and may enable unexpected file parsing behaviors that are not needed for the advertised functionality.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The metadata export examples encourage saving image information to JSON without warning that EXIF data may include GPS coordinates, device identifiers, timestamps, and other sensitive information. In an image-processing skill, users are likely to handle personal photos, so exporting and sharing this JSON can unintentionally disclose private data.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README advertises extraction of metadata and EXIF data but does not warn that such data can include GPS coordinates, device identifiers, timestamps, and other privacy-sensitive information. In a reusable skill that encourages exporting image information to JSON, this omission can lead users to unintentionally disclose personal or confidential data when sharing outputs or processing third-party images.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill explicitly supports extracting EXIF and metadata and saving the results to a file, but it does not warn that metadata may contain sensitive information such as GPS coordinates, device identifiers, timestamps, or authoring details. This can lead users to unintentionally disclose private information when sharing exported metadata or processed images that preserve embedded metadata.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly promotes extracting image metadata and EXIF data but does not warn that these fields can contain sensitive information such as GPS coordinates, device identifiers, timestamps, and authoring details. In an image-processing skill, this omission increases the chance that users will expose private data when inspecting, sharing, or exporting metadata.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The documentation describes batch processing and file generation workflows without explicitly warning about the risks of large-scale modification, overwriting, or unintended propagation of changes across many files. Although the examples use separate output directories, the absence of stronger safety guidance can still lead to user data loss or accidental destructive operations in practice.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The EXIF preservation example encourages copying metadata directly into output images without warning that EXIF may contain sensitive information such as GPS coordinates, device identifiers, timestamps, or authoring details. In an image-processing skill, this is contextually more dangerous because metadata retention is a common, easy-to-miss privacy leak when users expect transformed images to be sanitized.

Unpinned Dependencies

Low
Category
Supply Chain
Content
Pillow
openpyxl
Confidence
98% confidence
Finding
Pillow

Unpinned Dependencies

Low
Category
Supply Chain
Content
Pillow
openpyxl
Confidence
98% confidence
Finding
openpyxl

Known Vulnerable Dependency: Pillow — 10 advisory(ies): CVE-2016-2533 (Pillow buffer overflow in ImagingPcdDecode); CVE-2023-50447 (Arbitrary Code Execution in Pillow); CVE-2021-27922 (Pillow Uncontrolled Resource Consumption) +7 more

Critical
Category
Supply Chain
Confidence
94% confidence
Finding
Pillow

Known Vulnerable Dependency: openpyxl — 2 advisory(ies): CVE-2017-5992 (Improper Restriction of XML External Entity Reference in Openpyxl); CVE-2017-5992 (Openpyxl 2.4.1 resolves external entities by default, which allows remote attack)

High
Category
Supply Chain
Confidence
91% confidence
Finding
openpyxl

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal