Back to skill

Security audit

Toy Car to Real Car

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: its reported car-photo guidance aligns with its stated purpose, with a privacy note about uploading photos to a third-party service.

Before using the service, consider whether you are comfortable uploading the photo under its privacy and retention terms. Use a photo you are authorized to share, and consider removing location metadata or obscuring plates, faces, and identifying surroundings.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The workflow directs users to upload photos to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow encourages uploading car photographs to an external service without advising users to check for license plates, identifiable people, location clues, or embedded location metadata. Uploading is an explicit, user-controlled part of the requested service, and the skill prohibits agent uploads, which limits the risk; nevertheless, missing privacy guidance can lead to unintended disclosure under the service’s retention and reuse policies.

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 · LICENSE (reported line 11)May include surrounding context.

text
furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,