ClawHub
Back to skill

Security audit

Outline Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Chinese novel-outline generator, and its file access and dependencies are proportionate to that purpose.

Reasonable to install for local outline generation. Prefer installing in a virtual environment, review the output path before running because the script writes a Markdown file there, and consider pinning dependency versions if you need reproducible builds.

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 (3)

Unpinned Dependencies

Low
Category
Supply Chain
Content
pyyaml>=6.0.1
rich>=13.7.0
Confidence
93% confidence
Finding
The dependency is specified with a lower bound only, which allows future incompatible or compromised releases to be installed and makes builds non-reproducible. In a skill supply chain context, unpinned packages increase exposure to dependency confusion, malicious upstream changes, or accidental breakage.

Unpinned Dependencies

Low
Category
Supply Chain
Content
pyyaml>=6.0.1
rich>=13.7.0
Confidence
92% confidence
Finding
Using rich with only a minimum version permits unreviewed newer versions to be resolved at install time, which weakens reproducibility and supply-chain integrity. While not an immediate exploit by itself, it increases the attack surface if the upstream package is compromised or a breaking release is published.

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 requirement does not constrain the package to a clearly non-vulnerable reviewed version range. In an agent skill ecosystem, YAML is commonly used for configuration or content parsing, so if untrusted YAML is ever processed unsafely, these flaws can lead to code execution or other serious compromise.

Static analysis

No suspicious patterns detected.