ClawHub
Back to skill

Security audit

LiaoGong-OCR

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward OCR skill that processes user-selected images locally, with normal cautions around sensitive screenshots, dependency hygiene, and model downloads.

Install only if you are comfortable letting the agent OCR images you explicitly provide or reference. Avoid using it on screenshots containing secrets unless you intend the text to be extracted into chat or output files. Prefer a locked, updated environment for Pillow and numpy, and expect EasyOCR to download/cache model files on first use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The README advertises very broad trigger phrases like 'OCR this image' and '图片转文字' without any scoping, confirmation, or context constraints. In an agent ecosystem, generic triggers can cause unintended activation on unrelated user messages, resulting in unexpected file/image processing and possible data exposure from images that the user did not explicitly intend to send to this skill.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The statement that the AI assistant will 'automatically recognize' trigger phrases and call OCR is ambiguous and encourages implicit invocation behavior. That increases the risk of accidental skill execution in normal conversation, especially because OCR may process sensitive screenshots, documents, or photos containing private information.

Unpinned Dependencies

Low
Category
Supply Chain
Content
easyocr>=1.7.0,<2.0.0
pytesseract>=0.3.10
Pillow>=10.0.0
numpy>=1.24.0
Confidence
94% confidence
Finding
Pillow>=10.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
easyocr>=1.7.0,<2.0.0
pytesseract>=0.3.10
Pillow>=10.0.0
numpy>=1.24.0
Confidence
78% confidence
Finding
numpy>=1.24.0

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
97% confidence
Finding
Pillow

Known Vulnerable Dependency: numpy — 10 advisory(ies): CVE-2014-1859 (Numpy arbitrary file write via symlink attack); CVE-2021-41495 (NumPy NULL Pointer Dereference); CVE-2021-33430 (NumPy Buffer Overflow (Disputed)) +7 more

Critical
Category
Supply Chain
Confidence
83% confidence
Finding
numpy

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.