ClawHub
Back to skill

Security audit

FrameFerry

Security checks for vulnerabilities and agentic risk

Overview

FrameFerry is a disclosed public-media archiving skill with bounded local output and no hidden credential use or persistence.

Install only if you are comfortable running npm/Playwright setup and saving public media locally. Use a dedicated output directory, archive only public profiles you are allowed to preserve, and avoid CDP attachment to a personal browser profile unless you intentionally accept that browser-session exposure risk.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to execute shell commands (`npm ci`, Playwright install, and Node CLI runs) and write to arbitrary output paths, but it does not declare corresponding permissions. This creates a trust and policy gap: operators may approve or run the skill believing it is low-privilege when it can install dependencies, access environment state, and modify the filesystem.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
test/index.test.js:279