ClawHub
Back to skill

Security audit

batch-file-processor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward batch file summarization workflow, but users should avoid running it over sensitive directories unless they want those files processed by sub-agents.

Install only if you want agents to process multiple files from directories you choose. Do not aim it at repositories or folders containing secrets, credentials, private customer data, or personal files unless you are comfortable with summaries or extracted JSON containing that information; add redaction or tighter file selection for sensitive work.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
95% confidence
Finding
The skill explicitly instructs sub-agents to read files completely and return summaries or extracted data, but it provides no safeguards for handling secrets, credentials, personal data, or other sensitive content that may be present in those files. In a batch-processing context, this increases the chance of broad data exposure to multiple sub-agents and of sensitive information being propagated into JSON outputs, logs, or downstream reports.

Static analysis

No suspicious patterns detected.