Back to skill

Security audit

Founder

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only startup coaching skill with broad advice but no code, tools, data access, persistence, or hidden behavior.

Reasonable to install for general founder coaching. Treat its fundraising, hiring, runway, and mental-health-adjacent points as informal guidance, and use qualified professionals for legal, tax, investment, employment compliance, or medical decisions.

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
Confidence
93% confidence
Finding
The skill description is very broad and lacks clear activation boundaries or task constraints, which can cause the agent to invoke this skill in situations far outside startup coaching. Overly general business advice skills can overshadow more specific skills, increasing the risk of inappropriate guidance, context confusion, or accidental use in sensitive domains like finance, employment, or mental health adjacent decisions.

Static analysis

No suspicious patterns detected.