Security audit

VC 投前研究与初筛

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed VC research helper that returns markdown by default and only publishes externally after explicit user confirmation.

Before installing, note that the skill is Chinese-first and may need an explicit language request if you want another output language. Publishing to ima should only be used when you intentionally connect the ima MCP connector and confirm the destination and visibility.

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

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)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest description and title define the skill in Chinese and the prompt templates later instruct the model in Chinese, but the skill does not state that language is selectable by the user. This can violate language/locale policy because it implicitly fixes the interaction/output language rather than offering opt-in or choice.
Content: No source excerpt is available for this finding.