ClawHub
Back to skill

Security audit

Grant Writing Framework

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only grant-writing guide with one broad activation-quality issue but no hidden code, persistence, credential handling, or unsafe authority.

Installers should understand this skill may appear for some general funding or fundraising questions, but it is a content guide only. Users should still verify grant requirements, budgets, legal eligibility, and submission rules with the specific funder before relying on the generated proposal.

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
Confidence
94% confidence
Finding
The trigger phrases are broad enough to match many generic fundraising or funding-related requests, which can cause the skill to activate when the user did not specifically want a grant-writing framework. Over-broad activation can steer conversations into unintended domains, reduce user control, and increase the chance of irrelevant or policy-sensitive guidance being injected into normal interactions.

Static analysis

No suspicious patterns detected.