ClawHub
Back to skill

Security audit

FaceRating Photo Analysis Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent face-measurement guidance skill with clear safety boundaries, but its optional MCP setup runs an unpinned GitHub-hosted server that users should trust before installing.

Use the text-only guidance freely within its consent and adult-use boundaries. Only install the optional MCP if you trust the GitHub source and are comfortable with npx executing the current repository contents; a pinned release or commit would be safer.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The skill instructs users to launch an MCP server directly from a GitHub repository via npx -y github:... without pinning to an immutable version, tag, or commit. That creates a supply-chain risk: the referenced code can change after review, and anyone following the instructions may execute newly published or compromised code locally under their user context.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
- About: https://facerating.me/about
- Privacy: https://facerating.me/privacy
- Terms: https://facerating.me/terms
- Raw Skill: https://facerating.me/skills/facerating-photo-analysis-guide/SKILL.md
- MCP source: https://github.com/gpt-img-2/facerating-photo-analysis-mcp
- ClawHub listing: https://clawhub.ai/gpt-img-2/skills/facerating-photo-analysis-guide

Static analysis

No suspicious patterns detected.