ClawHub
Back to skill

Security audit

Grant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a grant-writing guidance document with no code, tool use, persistence, or hidden data access.

Installers should know this skill may activate for broad non-dilutive funding questions; review whether that routing is desirable, but there is no evidence of hidden access, execution, exfiltration, or persistence.

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

Medium
Confidence
97% confidence
Finding
The trigger description is broad enough that ordinary funding-related user requests may invoke this skill even when the user is not specifically asking for grant assistance. Overly broad activation increases the chance of unintended skill selection and unnecessary exposure of the skill's instructions in contexts where they are not the best fit.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation condition includes an open-ended catch-all for any scenario where someone is seeking non-dilutive funding, which can cause the skill to trigger outside narrowly defined grant-support contexts. While not directly enabling code execution or data exfiltration, this over-broad scope can lead to inappropriate routing, increased prompt exposure, and interference with more suitable skills.

Static analysis

No suspicious patterns detected.