slidev
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): A thorough review of all 56 files confirms they consist exclusively of Markdown documentation and reference materials. No obfuscation, hardcoded credentials, or malicious instructions were detected.
- [NO_CODE] (SAFE): The skill does not include any executable code, shell scripts, or automated configuration files (like package.json or requirements.txt). It operates purely as a knowledge base for the AI agent.
- [Indirect Prompt Injection] (LOW): As the skill enables the agent to read and modify Markdown-based presentation files, it introduces a surface for indirect prompt injection if the agent processes untrusted slides.
- Ingestion points: Markdown slide files (.md).
- Boundary markers: None identified in the provided documentation.
- Capability inventory: The skill documents capabilities for code execution (monaco-run), filesystem modification (monaco-write), and network exposition (via --tunnel and --remote CLI options).
- Sanitization: No specific sanitization or validation logic is provided within the skill for handling external data.
Audit Metadata