Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | `v1.0.4` | `v1.x` | 结构重构：全部内容内联进单一根目录 `SKILL.md`（平台拦截 `assets/`、`references/` 子目录文件） |
Security audit
忘情水会问版（禅意情感治愈类）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a documentation-style wrapper for a local narrative engine, with no hidden network access, credential handling, or automatic persistence beyond the app's expected local history feature.
Install only when you have the Mengpo narrative engine project and want a strict wrapper that preserves its existing story logic. Before running the optional selftest, review the copied script and run it from the intended engine directory because it will inspect and require local project modules.
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.