Back to skill

Security audit

Pop-cam NanoBanana

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Pop-cam image-generation API wrapper, with expected external data sharing that users should understand before use.

Install this only if you are comfortable sending prompts, source images, and related generation metadata to Pop-cam. Keep POPCAM_API_TOKEN private, avoid sensitive or regulated images unless you accept the third-party handling, and use webhook_url only with trusted HTTPS endpoints you control.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to send prompts and, in image-to-image mode, base64-encoded photos to Pop-cam's external API, but it does not clearly warn that this content leaves the local environment and is transmitted to a third party. This can cause users to unknowingly disclose sensitive images or prompt content, especially if they assume the skill operates locally.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This example explicitly transmits an Authorization token, prompt text, and image data to an external API endpoint. In context, external transmission is the intended function of the skill, but it still presents a real privacy and data-exposure risk if users send sensitive content without informed consent.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

Transform an existing photo:

bash
curl -X POST https://www.pop-cam.com/api/v1/nanobanana \
  -H "Authorization: Bearer $POPCAM_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The webhook section documents asynchronous delivery to a user-supplied webhook_url but does not clearly warn that generated results and associated job metadata will be POSTed to an external URL. Without an explicit warning, users may accidentally route generated content to untrusted or misconfigured endpoints, causing unintended disclosure.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 159)May include surrounding context.

md
## Prompt Tips

The model is **not limited to any single style**. The output depends entirely on your prompt. Here are example styles you can request:

| Style | Example prompt snippet |
|-------|----------------------|