ClawHub
Back to skill

Security audit

Funding

Security checks for vulnerabilities and agentic risk

Overview

This is a fundraising advice skill with broad activation wording, but it does not request tools, persistence, credentials, file access, or hidden authority.

Install only if you want fundraising, investor-pitch, donor, or crowdfunding guidance. Be aware it may activate on some general money-raising language, so users should clarify when they mean budgeting, debt, income, or other non-fundraising topics.

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
95% confidence
Finding

The skill’s trigger description is very broad and can activate on many generic requests about money, pitching, or persuasion. That overreach can cause the agent to invoke fundraising-specific guidance in contexts where the user did not intend investment or donation support, increasing the chance of irrelevant, manipulative, or policy-sensitive assistance being surfaced.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.