Back to skill

Security audit

model-cost-advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple model-cost advisory prompt/documentation file with no bundled code, persistence, credential handling, or privileged behavior.

Before installing, note that the skill appears to be mainly Chinese-language documentation and may require independent price verification because it claims live pricing but ships no code or data source implementation in the artifact. From a security perspective, it is low-risk based on the inspected files.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language sections switch to Chinese for core usage and feature explanation, which can impose a specific language on users without opt-in. The policy allows language constraints only when the skill offers a choice or clearly documents a justified locale limitation, which is not present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.