Back to skill

Security audit

nutrition-advisor-en

Security checks for vulnerabilities and agentic risk

Overview

This skill provides clearly scoped nutrition guidance and saves food records only with explicit user confirmation.

Expect English-language nutrition estimates for generally healthy adults. If enabling saved logs, review the fields and storage path carefully because the records are plaintext and may be accessible to local programs or 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 requires English-language support without user language opt-in.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The description instructs the agent to provide English-language nutrition support, but activation requires only a request for nutrition help, not consent to English output. No language choice or region-specific justification is provided.

Content

No source excerpt is available for this finding.