Back to skill

Security audit

生意人防坑顾问

Security checks for vulnerabilities and agentic risk

Overview

The skill's business-advice workflow is coherent, but it includes an off-platform WeChat payment/contact funnel for an unreviewed toolkit.

Install only if you are comfortable with a skill that may handle sensitive contract or chat content and that advertises an off-platform paid upgrade. Do not send payment screenshots, private business documents, or accept external scripts/toolkits through WeChat unless you independently trust the publisher and review those materials separately.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger text includes broad, everyday phrases such as users asking for help reviewing a cooperation or contract, which can match common conversation and cause the skill to activate when the user did not explicitly request this specific advisor. Unintended invocation can redirect user interactions, expose user-provided sensitive business documents to the wrong workflow, and degrade trust in routing behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill embeds a monetization funnel that directs users to add a personal WeChat account and send money off-platform to obtain additional functionality. This is dangerous because it bypasses platform trust and payment controls, enables social engineering and data exfiltration to an external contact channel, and pressures users into region-specific behavior without prior opt-in or necessity for the skill’s core function.

Content

No source excerpt is available for this finding.