Security audit
WBFlow·第5环 定妆图(一致性闸门)
Security checks for vulnerabilities and agentic risk
Overview
The skill creates character reference images and records their paths in the story file, with changes limited to its stated creative workflow.
Expect this skill to update story.json and create files under 05_chars. Review companion skills separately and confirm which image-generation service will receive character descriptions. Both scanners reported no findings; independent inspection supports that result. Unresolved scanner references are project inputs, generated outputs, or JSON fields.
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
Static analysis
No suspicious patterns detected.