Back to skill

Security audit

Generate Image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward HTML/URL-to-image API integration, but users should avoid sending sensitive HTML or private URLs to the third-party service.

Install only if you are comfortable sending the HTML, CSS, dynamic parameters, or public webpage URL to pdfapihub.com for rendering. Do not submit secrets, private internal URLs, session-bearing pages, confidential templates, or personal data unless you have approved that service for such use.

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
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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs users to send raw HTML content or a public URL to a third-party service, but it provides no warning about privacy, data handling, or the risks of transmitting sensitive page contents externally. This can lead users to unknowingly expose proprietary templates, embedded secrets, personal data, or internal-only URLs to an external processor.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The example usage demonstrates direct transmission of user-supplied HTML to an external API endpoint, confirming real external data flow rather than a hypothetical capability. If an agent uses this skill on sensitive content, the data leaves the local trust boundary and may be retained, logged, or processed by the third party.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Example Usage

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

text

## Notes
- Files are automatically deleted after 30 days
- Maximum output file size depends on your plan tier

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This JSON manifest-like file defines a capability but provides no natural-language restriction on when it should be invoked, what user intent it is meant to satisfy, or what requests should not trigger it. For manifest files, missing specificity around invocation scope can lead to unintended activation because there is no bounded description of appropriate use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The HTML template contains the fixed phrase "Hello {{name}}", which forces English output with no indication that the user can choose a language or locale. This is a natural-language policy concern because the skill bakes in a specific language rather than offering opt-in or configurability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.