Security audit
阅读教学指导
Security checks for vulnerabilities and agentic risk
Overview
ClawScan marked this Chinese reading and teaching guide skill benign, with no reported findings; its medium overall confidence reflects some unresolved references and notes about instruction scope and persistence.
The verdict is benign, and the scanners reported no security findings. Evidence is incomplete: Skillspector marked analysis partial because three local references in SKILL.md could not be resolved, although it scanned all 18 listed components. Consider whether this limitation and the noted uncertainty around instruction scope and persistence are acceptable before installing.
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
