Back to skill

Security audit

Huang Renxun Ai Strategy

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings; the only contextualized finding is a low-level concern about its prescribed output language.

The verdict is benign with high confidence, and Skillspector reports complete coverage of the two listed components. Consider whether the Chinese-primary output preference suits you before installing; 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 skill prescribes Chinese as the primary output language without user opt-in.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The language setting specifies primarily Chinese output with English technical terms retained. It offers no user language choice or opt-in and does not justify why the skill's general AI strategy analysis requires this language restriction.

Content

No source excerpt is available for this finding.