isolated-vm
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or high-risk behaviors were detected in the skill instructions or metadata.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from the official isolated-vm GitHub repository. This is a standard and safe practice for a documentation-focused skill referencing a reputable source.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing external documentation from a remote repository, which presents a surface for indirect instructions.
- Ingestion points: Sub-agent fetches the README.md from the laverdet/isolated-vm repository via GitHub User Content.
- Boundary markers: The provided prompt templates do not include specific delimiters or instructions to ignore embedded commands in the documentation.
- Capability inventory: The skill itself lacks command execution, network exfiltration, or file system modification tools.
- Sanitization: No content sanitization or validation is performed on the fetched documentation.
Audit Metadata