Back to skill

Security audit

Product Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only product-manager persona skill with no install steps, executable code, credential access, or persistence behavior.

This skill appears appropriate if you want a product-management advisor and document-template assistant. Users should understand that it may respond to broad product-management requests because the activation language is general, but the artifacts do not show privileged or unsafe behavior.

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 markdown says to use the agent by name or specialty whenever its expertise is needed, but it does not define specific trigger phrases, scope boundaries, or exclusion conditions. Phrases like invoking by "specialty" are broad enough to overlap with common product-management requests and could cause unintended activation.

Content

No source excerpt is available for this finding.