ClawHub
Back to skill

Security audit

Mp Grill Me

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight planning-review prompt that asks probing questions and may inspect the current codebase, with no scripts, persistence, credentials, or network behavior found.

Install this if you want an agent to actively challenge plans and designs one question at a time. Be aware that it may inspect the current codebase to answer its own review questions, so use it in workspaces where that level of local code access is acceptable.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language is broad and overlaps with many normal planning or design-discussion requests, such as reviewing plans, discussing designs, or asking to be 'grilled.' In an agent-routing context, this can cause the skill to activate when the user did not clearly request this specialized behavior, leading to unintended interrogation-style interactions and possible inappropriate codebase exploration.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The description mixes English and Chinese without stating that language choice follows the user's preference. This can create unexpected routing or presentation behavior for users who did not opt into multilingual handling, potentially causing confusion or accidental skill matching across languages.

Content

No source excerpt is available for this finding.