Security audit

产业链潜力股挖掘

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Cue-powered financial research workflow, with expected cautions around stock-screening outputs, API-key use, external service calls, and local report/session files.

Install only if you are comfortable sending research queries to Cue, using a Cue API key, and possibly consuming Cue credits. Treat outputs as investment research and verify sources independently before making financial decisions.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Description-Behavior Mismatch

Medium

Confidence: 92% confidence
Finding: The skill states it does not provide buy/sell recommendations, but its example prompts and positioning still steer users toward investment selection by asking which segment is 'most worth watching' and which securities have the 'largest elasticity.' This creates a deceptive safety boundary and can nudge an agent into producing quasi-investment recommendations despite the stated limitation.

Static analysis

No suspicious patterns detected.