Back to skill

Security audit

nutrition-advisor

Security checks for vulnerabilities and agentic risk

Overview

This Chinese-language nutrition skill has clear limits and requires confirmation before saving personal dietary records.

Use this for everyday nutrition estimates, not medical treatment. Before enabling saved logs, review the fields and storage location; plaintext files may be accessible to other local programs and backups.

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 skill specifies Chinese-language nutrition support without user opt-in or a justified locale constraint.

Low
Category
Output Handling
Confidence
92% confidence
Finding

The description explicitly specifies “提供中文日常营养支持” (provide Chinese-language daily nutrition support). This imposes a language requirement without offering a language choice or explaining a region-specific need.

Content

No source excerpt is available for this finding.