ClawHub
Back to skill

Security audit

JSON Wizard

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward local JSON/YAML formatting tool with no hidden network, persistence, or privileged behavior found.

Install only if you are comfortable using a local Python tool to process JSON/YAML you provide. Prefer installing with a reviewed, pinned PyYAML version, and avoid using --file on sensitive files unless you intend the tool to read and print their parsed contents.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Unpinned Dependencies

Low
Category
Supply Chain
Content
pyyaml>=6.0
Confidence
95% confidence
Finding
The dependency is specified as `pyyaml>=6.0`, which allows future unreviewed versions to be installed and makes builds non-reproducible. In a tool that validates and converts JSON/YAML, dependency behavior is security-relevant, so leaving the version open-ended increases the chance of pulling in a breaking or vulnerable release unexpectedly.

Known Vulnerable Dependency: pyyaml — 8 advisory(ies): CVE-2019-20477 (Deserialization of Untrusted Data in PyYAML); CVE-2020-1747 (Improper Input Validation in PyYAML); CVE-2020-14343 (Improper Input Validation in PyYAML) +5 more

Critical
Category
Supply Chain
Confidence
88% confidence
Finding
PyYAML has a history of deserialization and input-validation vulnerabilities, and this skill explicitly processes JSON/YAML supplied by users. That context makes the dependency more dangerous than in a non-parser tool, because malformed or malicious YAML could reach vulnerable code paths if unsafe loading or affected versions are used.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.