ClawHub
Back to skill

Security audit

Agentic Browser Workflow Templates

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local workflow-template generator and does not show hidden browser execution, network access, credential handling, or persistence.

Before installing, treat this as a local helper that may read a JSON steps file you point it at and may write a generated template to a path you choose. Avoid passing sensitive files as `--steps`, and choose an output path you are comfortable letting the skill create or overwrite.

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
83% confidence
Finding
The skill advertises generation of workflow templates and explicitly accepts file paths for `--steps` and `--output`, which implies file read/write capability, but it does not declare any tool scope or permission boundaries. In an agent setting, undeclared file access weakens least-privilege controls and can allow broader-than-expected access to local data or writes if the surrounding platform infers or grants capabilities implicitly.

Static analysis

No suspicious patterns detected.