ClawHub
Back to skill

Security audit

Donor Update

Security checks for vulnerabilities and agentic risk

Overview

This is a donor-stewardship writing guide with no code execution, persistence, credential access, or hidden behavior.

Review generated donor messages before sending, especially any placeholder impact figures or stories, but the skill itself only drafts stewardship copy and does not access donor systems or send messages.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (2)

Self-Modification

High
Category
Rogue Agent
Content
}
---

# Donor Update Skill

Donor retention is cheaper than acquisition and runs on one feeling: *my gift mattered and I'm appreciated.*
A stewardship update delivers that — thank them sincerely, show the concrete impact of their support, and make
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill advertises very broad trigger phrases such as writing a donor update, thank-you email, supporter newsletter, or gift acknowledgement, which can overlap with many ordinary fundraising or CRM-related requests. Without clearer activation boundaries, an agent may invoke this skill in contexts where a different workflow, compliance review, or human approval is expected, causing unintended automated outreach or inappropriate donor messaging.

Static analysis

No suspicious patterns detected.