ClawHub
Back to skill

Security audit

LiteParse Document Parser

Security checks for vulnerabilities and agentic risk

Overview

LiteParse is a coherent local document parsing skill whose file output and OCR examples are expected for its stated purpose.

Install only if you want a local document parsing CLI. Review Homebrew package provenance as you would for any CLI tool, and direct outputs or screenshots to paths where overwriting files would not matter.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Low
Confidence
86% confidence
Finding
This markdown file documents commands that create output files and directories such as `./output-directory`, `output.json`, and `./screenshots`. Under the missing-warning rule for markdown, the description should disclose behaviors that affect user data or the local filesystem, but no warning about file creation or overwriting is provided near these examples.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The markdown shows `--ocr-language fra` and a config example with `ocrLanguage: "en"`, which together imply language-specific behavior. Because the documentation does not explicitly offer user opt-in or explain locale selection policy, this can be read as forcing a language/locale choice without clear user guidance.

Static analysis

No suspicious patterns detected.