100Critical
This skill is vulnerable to arbitrary
Behavior Analysis
Mismatch detected — The skill's description implies it directly performs 'sequential image generation'. However, the detailed workflow shows it delegates the actual image generation to an 'installed image generation skill' and image compression to system tools, acting as an orchestrator rather than a direct image creator.
Claims to do
Knowledge Comic Creator: Create original knowledge comics with flexible art style × tone combinations.
Actually does
The skill processes input content and user options to generate a storyboard, character definitions, and image prompts. It then orchestrates comic creation by invoking an external image generation skill to produce comic pages and character sheets, optionally compressing images using `sips` or `pngquant`. Finally, it uses `scripts/merge-to-pdf.ts` (executed via `bun` or `npx`) to merge the generated images into a PDF.
Skill Info
Namejimliu/baoyu-skills/baoyu-comic
Registrygithub
Versione13092ba2af1
PURLpkg:github/jimliu/baoyu-skills@e13092ba2af1?skill=baoyu-comic
Stars14,596
Installs15,300
Source
SHA-256a2665a1e51b1...
SHA-189929339c971...
MD56bc282335ec0...
TLSH1162d7760cc3...
ssdeep384:xf0m4qOy...
Size15,140 bytes
Install
Assessments (3)
AI Agent Traps ↗Arbitrary Code Execution via Script Runnercriticalcommand execution
The skill explicitly defines a mechanism to execute TypeScript scripts using 'bun' or 'npx'. If script names or arguments are not properly sanitized, this can lead to arbitrary code execution.
100% confidenceline 124
Agent Execution Instructions:
1. Determine this SKILL.md file's directory path as `{baseDir}`
2. Script path = `{baseDir}/scripts/<script-name>.ts`
4. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`External Command Execution for Image Processingcriticalcommand execution
The skill directly invokes system commands like 'sips' (macOS) and 'pngquant' for image compression. Lack of input sanitization for file paths could allow command injection.
100% confidenceline 220
Or system tools: `sips -s format jpeg -s formatOptions 80 input.png --out output.jpg` (macOS) Or: `pngquant --quality=65-80 input.png -o output.png`
Potential Path Traversal in Output Directoryhighdata exfiltration
The output directory path `comic/{topic-slug}/` uses a user-derived 'topic-slug'. Insufficient sanitization of this slug could enable path traversal attacks, leading to arbitrary file writes or reads.
80% confidenceline 115
Output directory: `comic/{topic-slug}/`
Slug: 2-4 words kebab-case from topicSub-Agent Spawning and Tool Use Dependencyhighsub agent spawning
The skill invokes an external image generation skill (e.g., 'baoyu-imagine'). This introduces a supply chain risk, as vulnerabilities or malicious intent in the invoked skill could be exploited.
90% confidenceline 200
Invoke an installed image generation skill such as `baoyu-imagine` Read that skill's `SKILL.md` and follow its documented interface
Reliance on External Configuration File (EXTEND.md)mediummemory poisoning
The skill loads configuration from `EXTEND.md` in specific user or project directories. If an attacker can modify this file, they could poison the agent's preferences or introduce malicious configurations.
80% confidenceline 250
CRITICAL: If EXTEND.md not found, MUST complete first-time setup... Path: `.baoyu-skills/baoyu-comic/EXTEND.md` | `$HOME/.baoyu-skills/baoyu-comic/EXTEND.md`
Description Mismatchlowdescription mismatch
The skill's description implies it directly performs 'sequential image generation'. However, the detailed workflow shows it delegates the actual image generation to an 'installed image generation skill' and image compression to system tools, acting as an orchestrator rather than a direct image creator.
85% confidence
Description: 'Creates original educational comics with detailed panel layouts and sequential image generation.' Workflow: 'Invoke an installed image generation skill such as `baoyu-imagine`', 'Use available image compression skill (if any) Or system tools: `sips`... Or: `pngquant`...'
Dependencies (1)
baoyu-skills.claude-plugin/marketplace.jsonnot scanned
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/jimliu/baoyu-skills/baoyu-comic)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/jimliu/baoyu-skills/baoyu-comic"><img src="https://mondoo.com/ai-agent-security/api/badge/github/jimliu/baoyu-skills/baoyu-comic.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/jimliu/baoyu-skills/baoyu-comic.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow