ClawHub
Back to skill

Security audit

General OCR Struct

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local OCR helper that reads user-provided image files and prints extracted or structured text without hidden network, persistence, or privilege behavior.

This appears appropriate to install if you want local OCR. Be aware that images such as receipts, card statements, and chat screenshots can contain sensitive personal or financial information, so only run it on files you intend to process locally and review OCR output before using it downstream.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

python3 scripts/general_ocr.py transactions /path/to/image.jpg --json

text

## Output rules

- Prefer showing the recognition result first, then the cleaned structure.
- Preserve source wording where possible.

Static analysis

No suspicious patterns detected.