Back to skill

Security audit

Code Review ProMax

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners reported one low-severity issue about a required Chinese heading, and no other findings, though one reference could not be resolved.

The verdict is benign, but the evidence is incomplete: Skillspector could not resolve one local path-like reference. Consider whether the fixed Chinese heading is acceptable for your use, and bear in mind that benign does not mean risk-free.

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 mandatory fix-instruction heading forces Chinese text even for users requesting English output.

Low
Category
Output Handling
Confidence
96% confidence
Finding

The skill requires the generated heading to remain ## Code Review 修复任务, and repeats that requirement in the English output instructions at L254. This imposes Chinese text without opt-in, contradicting the user-language matching rule at L21.

Content

No source excerpt is available for this finding.