Security audit

餐厅装修避坑指南

Security checks for vulnerabilities and agentic risk

Overview

This dining-room renovation guide uses bundled reference articles and requests no sensitive access, external data transfers, or executable actions.

Use the articles as design inspiration; some contain duplicate content and extraction errors. Have qualified professionals verify structural, electrical, and plumbing changes.

A.I.G

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

SkillSpector

Vulnerability Patterns

Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
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

Findings (2)

Context Window Stuffing

Medium

Category: Memory Poisoning
Confidence: 80% confidence
Finding: Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
Content: Scanner excerpt · references/ref-028.md (reported line 56)May include surrounding context.
md
9000 ACX SCFT 310005348 (123414830223403022330024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400 ▲一体转角成就空间的完整，各自又独立满足收纳，视觉更统一，空间更完整

Context Window Stuffing

Medium

Category: Memory Poisoning
Confidence: 80% confidence
Finding: Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
Content: Scanner excerpt · references/ref-029.md (reported line 8)May include surrounding context.
md
9000 ACX SCFT 310005348 (123414830223403022330024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400240024002400 ▲一体转角成就空间的完整，各自又独立满足收纳，视觉更统一，空间更完整

Static analysis

No suspicious patterns detected.