Security audit

AI KEY·风口在哪

Security checks for vulnerabilities and agentic risk

Overview

This trend-analysis skill fits its stated purpose, but users should review its memory behavior and supply missing setup files before use.

Review and supply the missing configuration and shared rules before use. Confirm the memory directory is private to you and decide whether business judgments and behavioral notes should persist; establish review and deletion preferences. All bundled files were inspected, but the absent configuration and shared rules remain unverified.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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 (1)

The skill instructs the agent to persist user judgments and behavioral observations without requiring a user-facing privacy notice.

Medium

Category: Output Handling
Confidence: 91% confidence
Finding: The skill directs the agent to persist users’ judgments and behavioral observations for future interactions without requiring a user-facing notice or permission. These records may reveal business plans or personal decision-making patterns, creating privacy risks through unexpected retention, later reuse, or access to the configured memory store. The intended personalization purpose, source labeling, and absence of external transmission reduce suspicion, but do not establish informed consent or retention limits.
Content: No source excerpt is available for this finding.