Back to skill

Security audit

founder-playbook

Security checks for vulnerabilities and agentic risk

Overview

This text-only founder coaching skill fits its stated purpose and shows no hidden execution, credential access, or data export.

Use it for founder decision discussions and share only business or personal details you are comfortable putting into chat. Its broad trigger examples may invoke coaching unexpectedly. Verify dated funding, legal, and treasury information before acting. All bundled files were inspected; the scanner's partial status did not reveal a missing executable component.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/coaching-techniques.md (reported line 98)May include surrounding context.

md
### Reality Questions

Understand current situation without judgment:

- "Where are you now on a scale of 1-10?"
- "What's happening at the moment?"

Activation examples include everyday phrases without an explicit startup-context requirement.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The description lists "should I", "help me think through", and "what am I missing" as invocation examples, although these phrases routinely occur in unrelated requests. While the description identifies founders as its audience, it does not explicitly require a founder or startup decision context for these triggers or provide exclusions, risking unintended coaching invocations.

Content

No source excerpt is available for this finding.