Back to skill

Security audit

引导式创作艺术家

Security checks for vulnerabilities and agentic risk

Overview

This is a creative writing and image-prompt helper with no hidden local access, persistence, or unsafe execution in the inspected artifact.

Install this as a creative-assistance skill. Be aware that if you ask it to generate an image directly, it may invoke a separate image-generation skill or provider workflow, so review that image tool's own permissions and costs separately.

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
92% confidence
Finding

The table mandates that prompts for 即夢 / 可靈 use '中文自然描述', which imposes a specific language requirement. Under the policy, language constraints should either offer opt-in/choice or be clearly justified as region-specific; this file does neither.

Content

No source excerpt is available for this finding.