Back to skill

Security audit

胡田 OPC导师 路演管理

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese roadshow-management template skill with expected business and contact-data workflows, and I found no hidden code, automatic access, or deceptive behavior.

Install only if a Chinese-language roadshow workflow fits your needs. Before using it with real projects or investors, decide where records will be stored, who may access them, how contact details and commercial information will be shared, and when exported data or replay/Q&A records should be deleted.

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
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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill description and usage instructions are written only in Chinese, with no indication that other languages are supported or that Chinese is an intentional, region-specific requirement. This can violate language/locale policy when users are not given an explicit choice or opt-in for a forced language.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructs AI to generate meeting minutes, summarize investor questions, and track financing, valuation, team, and risk details, all of which can contain sensitive business information and potentially personal data. Without guidance on data minimization, consent, retention, redaction, or secure storage, users may expose confidential startup information or regulated personal data to downstream systems or unauthorized parties.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template explicitly includes collection of named contact person details and contact methods, but provides no privacy notice, lawful-basis guidance, retention rules, access controls, or handling restrictions. In a business matchmaking database, this can lead to unnecessary collection, over-sharing, or misuse of personal information, creating privacy, compliance, and reputational risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The SOP directs operators to collect, export, share, and follow up on investor and project-related data such as participation records, Q&A logs, replay links, and intention forms, but it does not mention consent, privacy notice, retention, access control, or lawful handling of personal information. In a business matchmaking and livestream context, this can expose contact details, investment interest, and other sensitive commercial data to unauthorized use or over-sharing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The natural-language instructions and description consistently require Chinese reading ability, effectively forcing a specific language for use of the skill. Under the policy, locale or language constraints should either be optional for the user or explicitly documented as a justified regional constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains user-facing instructions and field labels exclusively in Chinese, which can impose a specific language on users without any opt-in or justification. The policy calls for flagging language or locale constraints unless the file offers a choice or clearly documents that the skill is intended for a specific regional context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing guidance exclusively in Chinese, and there is no indication that the skill is intentionally limited to Chinese-speaking users or a region-specific workflow. Under the language/locale policy, forcing a single language without user opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.