Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 按需求主题加载对应 `SKILL.md`：
Security audit
minemap-skills
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-style MineMap coding skill with no bundled executable behavior, persistence, or hidden high-impact access.
Install this as a MineMap coding reference, not as a complete reviewed bundle of every linked sub-skill. Review any additional sub-skill files or upstream content before adding them, and only use trusted MineMap CDN/model URLs and your own authorized key/solution values.
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)
Static analysis
No suspicious patterns detected.