ClawHub
Back to skill

Security audit

Grill Me

Security checks for vulnerabilities and agentic risk

Overview

This is a small prompt-only skill for challenging a user's plan, with no executable code, persistence, credential handling, or hidden data flow.

Install this if you want an agent to rigorously question plans and designs. Be aware that when a plan relates to repository code, the skill may lead the agent to inspect project files to answer its own questions, so invoke it in workspaces where that kind of review is intended.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation cue includes broad, natural-language triggers such as 'stress-test a plan' and 'grill me', which can plausibly appear in ordinary conversation and cause unintended invocation. In this skill’s context, accidental activation is more concerning because the body instructs the agent to 'explore the codebase instead' when questions can be answered that way, potentially leading to unnecessary repository inspection or scope expansion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.