Security audit

VC LP 报告与知识管理

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed VC reporting and knowledge-answering skill with optional user-confirmed publishing, not hidden or destructive behavior.

Before installing, users should be aware that LP reports and fundraising materials can contain sensitive fund, portfolio, and LP information. The skill appropriately requires explicit confirmation before publishing to ima, but users should still review and redact confidential content before any external publication.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The trigger description includes broad keywords such as “募资”, “知识库问答”, “引用”, and “认知” without defining required combinations, context, or exclusions. In a markdown skill description, this can cause unintended invocation because ordinary user requests may contain these terms even when the skill is not the best fit.
Content: No source excerpt is available for this finding.