Back to skill

Security audit

Fundraising Faq

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow fundraising-prep writing skill with no code execution, persistence, credential use, or hidden data access.

Install this if you want structured help preparing for fundraising Q&A. Review generated answers carefully because the skill may infer assumptions from a short brief and is designed to produce confident investor-facing language, even though it tells the agent to mark assumptions and stay honest.

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
  • 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
91% confidence
Finding

The skill description is broadly phrased to trigger on many common fundraising-related requests such as investor Q&A prep, pushback handling, and FAQ building, without clear activation boundaries or exclusions. This can cause over-invocation in loosely related conversations, increasing the chance the skill is applied when the user did not explicitly ask for fundraising-prep behavior and potentially steering responses toward pre-scripted persuasive content.

Content

No source excerpt is available for this finding.