ClawHub
Back to skill

Security audit

batch-file-processor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward batch file processing helper whose main risk is intentional full-file reading across user-selected directories.

Install only if you are comfortable with the agent reading complete contents of the files in the directory you ask it to process. Avoid pointing it at directories containing secrets, credentials, personal records, or confidential business data unless that is intentional.

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
  • 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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to read files completely and distribute their contents to parallel sub-agents, but it provides no user-facing warning about bulk data access or propagation to additional processing contexts. This can cause unintended exposure of sensitive or private file contents, especially when users invoke the skill for large directories without realizing that multiple sub-agents will each receive raw data.

Content

No source excerpt is available for this finding.