ClawHub
Back to skill

Security audit

PDF Parse

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PDF parsing API wrapper, but users should understand that PDFs or PDF URLs are processed by pdfapihub.com.

Install only if you are comfortable sending selected PDFs or public PDF URLs to pdfapihub.com with an API key. Avoid confidential, regulated, or highly personal documents unless that third-party processing is approved for your use case.

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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs users to provide either a public URL to a PDF or upload a file, and later directs requests to a third-party API service, but it does not clearly disclose that document contents will be transmitted off-platform to that external provider. This omission is dangerous because users may submit sensitive PDFs such as invoices, resumes, contracts, or forms without informed consent about third-party data exposure.

External Transmission

Medium
Category
Data Exfiltration
Content
## Example Usage
```bash
curl -X POST https://pdfapihub.com/api/v1/pdf/parse \
  -H "CLIENT-API-KEY: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{ "url": "https://pdfapihub.com/sample-pdfinvoice-with-image.pdf", "mode": "full", "pages": "1-3" }'
Confidence
89% confidence
Finding
The example usage shows a POST request sending user-supplied PDF data to an external domain, which confirms external transmission of potentially sensitive document content. In the context of this skill, that behavior is expected for functionality, but it still creates real confidentiality and compliance risk if users process private PDFs without explicit warning or trust review of the third-party service.

Vague Triggers

Low
Confidence
87% confidence
Finding
This manifest provides the skill name and description but does not define any explicit trigger phrases, activation boundaries, or exclusion conditions. In manifest files, the absence of trigger specificity can make it unclear when the skill should be invoked versus when a general PDF-related request should be handled differently.

Static analysis

No suspicious patterns detected.