Back to skill

Security audit

wanxiang-gtm

Security checks for vulnerabilities and agentic risk

Overview

This is a simple GTM content-writing skill with no code, external access, persistence, or hidden behavior.

Installers should understand that this skill may be invoked for a fairly broad set of new-feature marketing and sales-writing requests. Review generated GTM, PR, and competitor-comparison content for accuracy and tone before external use.

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
  • 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
94% confidence
Finding

The skill declares activation conditions that are extremely broad, including vague references like any mention of a 'new feature' plus a need for customer-facing output, and even says it should be used when GTM is not explicitly requested. This can cause the agent to invoke the skill in unintended contexts, leading to irrelevant or policy-bypassing content generation and increasing the attack surface for prompt-routing abuse.

Content

No source excerpt is available for this finding.