ClawHub
Back to skill

Security audit

YC New Way

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only startup planning skill with proportionate guidance and no executable, persistence, credential, or hidden data-handling behavior.

Installers should expect this skill to influence startup-planning requests toward a YC-style validation sprint. Review generated plans before posting in communities, adding analytics, or collecting emails, and ensure any outreach complies with site rules and applicable privacy requirements.

A.I.G

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

SkillSpector

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
90% confidence
Finding

The skill description includes broad activation phrases such as 'turn a vague idea into a testable plan' and 'design a 7-day startup sprint,' which can match many generic startup or planning requests. This creates over-broad routing risk: the skill may activate in contexts the user did not explicitly intend, causing the agent to apply this playbook inappropriately and potentially overshadow more suitable, narrower skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.