Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
Cad Mesh 3dgs
Security checks for vulnerabilities and agentic risk
Overview
This is a domain guidance skill for CAD, mesh, and 3D Gaussian Splatting workflows, with no executable payload or hidden high-impact behavior found.
Before installing, treat this as a research aid rather than an authoritative source: verify cited methods and dates, especially newer 2025-2026 claims. Security-wise, it is a passive Markdown skill with no observed automatic actions or sensitive access.
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 (2)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill instructs the model to use fixed response templates and includes a rule to cite uncertain information as "[需验证]", which strongly suggests a forced Chinese output convention without explicit user opt-in. This is dangerous because it can override user language preference, reduce usability, and create a mild prompt-control issue where the skill constrains output behavior beyond task requirements.
- Content