ClawHub
Back to skill

Security audit

grill-with-docs

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning workflow that creates project requirement and domain-modeling documents, with no evidence of hidden execution, credential use, or data exfiltration.

Before installing, expect this skill to guide the agent through an extended requirements conversation and to create or update planning documents such as CONTEXT.md and ADRs. Review those document changes before accepting them in an important project.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: grill-with-docs
description: "Combine brainstorming deep-dive with domain modeling for precise requirement exploration"
tags: [planning, general, iterative, memory-based, file-based]

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger example is very generic ('I want to design a new XX feature') and closely matches ordinary planning or product-design requests. In systems that auto-route or suggest skills based on examples, this can cause over-triggering, making the agent invoke this composite skill unexpectedly and steer conversations into unnecessary document creation or workflow changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.