Back to skill

Security audit

Scento Perfume Data

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly disclosed perfume lookups through Scento, with access proportionate to that purpose.

Perfume searches and preferences will be sent to Scento, so keep queries limited to information needed for the lookup. The scanner reported complete coverage, and independent inspection covered the entire one-file package; live service behavior and data retention were not verified.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The search workflow sends user-derived perfume queries to Scento without a privacy notice.

Low
Category
Output Handling
Confidence
86% confidence
Finding

The skill instructs the agent to search Scento's external API, which transmits search terms derived from the user's request. Although the API and its read-only nature are documented, the skill does not warn that these terms are shared with a third-party service; read-only access does not prevent that disclosure.

Content

No source excerpt is available for this finding.