Back to skill

Security audit

Founder OS

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only startup-advice skill; its triggers are broad, but it does not run code or request sensitive access.

Installers should expect this skill to shape the agent into a structured startup advisor when common founder-advice phrases are used. Review the advice critically, especially around legal, finance, immigration, fundraising, compensation, and health-related founder-resilience topics, and use qualified professionals where decisions have real consequences.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger "Validate my startup idea" is broad enough to overlap with ordinary user conversation, so the skill may activate unintentionally when a user is simply asking for general advice. Unintended invocation can override the agent's normal routing or inject this skill's strong behavioral framing into contexts where the user did not explicitly request the Founder OS workflow.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger "Review my pitch deck" is a common, generic request that could appear in many unrelated advisory or document-review contexts, creating a risk of accidental skill activation. Because this skill contains a comprehensive operating framework, accidental routing may cause the system to apply founder-specific instructions or structured flows without clear user intent.

Static analysis

No suspicious patterns detected.