ClawHub
Back to skill

Security audit

Donor Message

Security checks for vulnerabilities and agentic risk

Overview

This is a benign donor-communication writing helper with only minor trigger-scope looseness.

Safe to install as a writing aid. Users should provide only donor details they are comfortable using in generated messages and review drafts for accuracy, privacy, and compliance with their organization's donor-communication practices.

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 (2)

Vague Triggers

Low
Confidence
83% confidence
Finding
The description says to use the skill when fundraisers need to communicate with donors or supporters, which is a wide condition that may match many ordinary writing requests without clearly delimiting when this skill should or should not activate. The file gives examples, but it does not provide exclusions or constraints to narrow the trigger scope.

Vague Triggers

Low
Confidence
88% confidence
Finding
The phrase 'User asks how to communicate with supporters effectively' is broad and could overlap with many general advice requests, making unintended invocation more likely. It does not specify donor-message formats, channels, or fundraising context tightly enough to distinguish this skill from generic communication help.

Static analysis

No suspicious patterns detected.