ClawHub
Back to skill

Security audit

Image to PDF

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent image-to-PDF API integration, but it encourages processing sensitive images through a third-party service and default hosted PDF URLs without enough user-facing data-handling disclosure.

Review this before installing if you may convert IDs, medical records, insurance photos, business documents, or other confidential images. The skill sends image data or image URLs to pdfapihub.com and may return PDFs hosted on a pdfapihub CDN; use it only for content you are authorized to share with that provider and only if its privacy, retention, and access-control terms are acceptable.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs users to provide image URLs, base64 images, or uploaded files and states that requests are sent to pdfapihub.com, but it does not clearly warn that potentially sensitive image contents will be transmitted to a third-party service. Because the documented use cases include medical records, IDs, insurance claims, and real-estate photos, users may unknowingly send regulated or highly sensitive data off-platform, creating privacy, compliance, and data-handling risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The example usage shows a POST request that sends user-supplied image references and an API key to an external domain, confirming external data transmission. In this skill's context that behavior is expected functionality, but it is still security-relevant because users may process sensitive images and may not understand that both content and metadata are leaving the local environment for third-party handling.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

Example Usage

bash
curl -X POST https://pdfapihub.com/api/v1/convert/image/pdf \
  -H "CLIENT-API-KEY: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example shows user-supplied images being sent to a third-party service at pdfapihub.com, which contradicts a local-conversion-style description and creates a data disclosure risk. Images may contain sensitive information, and undisclosed transfer to an external processor can violate user expectations, privacy requirements, or data handling policies.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Returning a third-party hosted pdf_url means generated documents are stored and served from an external CDN, extending the skill from pure conversion into external document hosting. This increases exposure because converted files may remain accessible outside the user's environment, with unclear retention, access control, or sharing semantics.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is explicitly configured to send user-supplied images or image URLs to an external third-party service at pdfapihub.com, but the manifest provides no user-facing warning that image content leaves the local environment. Images often contain sensitive personal or business information, so silent transmission to a remote API can create confidentiality and compliance risks even if the service itself is legitimate.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This JSON file is a manifest/example-style file, so vague-trigger checks apply. It describes a conversion capability and external API call structure but provides no explicit trigger phrases, scope limits, or exclusion conditions, which can make invocation conditions ambiguous in systems that derive behavior from manifest descriptions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.