ClawHub
Back to skill

Security audit

Millimetric Query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Millimetric analytics helper whose commands match its stated purpose, with privacy care needed for raw and per-user event queries.

Install only if you are authorized to access the Millimetric workspace tied to the read key. Treat raw events and user-specific queries as potentially sensitive behavioral data, prefer aggregate reports when possible, and avoid sharing outputs that include user identifiers or activity timelines.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly documents raw event queries and a user-specific lookup (`user_id=user_42`) without any privacy warning, minimization guidance, or access-control caveat. Even though the API key is described as read-only, read-only access to analytics can still expose sensitive behavioral data, identifiers, attribution metadata, and user activity timelines that may be misused for profiling or inappropriate surveillance.

Static analysis

No suspicious patterns detected.