ClawHub
Back to skill

Security audit

Image OCR Parse

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed cloud OCR integration that uploads user-selected images to PDFAPIHub and does not show hidden execution, persistence, or unrelated data access.

Install this only if you are comfortable sending OCR images to PDFAPIHub with your API key. Do not upload IDs, medical records, invoices, screenshots with secrets, or other sensitive images unless you have permission and trust the provider's retention and privacy practices.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

External Transmission

Medium
Category
Data Exfiltration
Content
## Example Usage
```bash
curl -X POST https://pdfapihub.com/api/v1/image/ocr/parse \
  -H "CLIENT-API-KEY: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The request body sets "lang": "eng", and the response also reflects English as the language, which indicates the skill is configured to force a specific language/locale. For all file types, this is a policy concern unless the skill offers user choice or clearly documents why the locale restriction is required.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly sends user-supplied images to a third-party cloud OCR service, but the manifest does not clearly warn users that image contents may leave the local environment and be processed externally. This creates a real privacy and data-handling risk, especially if users submit IDs, invoices, medical documents, screenshots, or other sensitive images under the assumption that processing is local or low-risk.

Vague Triggers

Low
Confidence
82% confidence
Finding
This JSON manifest-like example shows a request/response shape but provides no information about when this skill should be invoked or what user intent should trigger it. For manifest files, missing specificity on trigger scope or constraints can cause unintended invocation if this file is used as part of skill activation metadata.

Static analysis

No suspicious patterns detected.