Security audit
Skill Panorama(技能全景图生成)
Security checks for vulnerabilities and agentic risk
Overview
This documentation-only skill describes creating branded charts and contains no harmful execution, hidden data collection, or persistent changes.
Provide the skill descriptions and branding assets needed, and choose where outputs should be saved. The missing README leaves a documentation gap, and image generation depends on your agent's existing capabilities. Metadata says MIT, while the bundled licensing text reserves rights over the documents; check those terms before redistribution.
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
