page-import
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external URLs which could contain malicious instructions designed to influence the agent's behavior. \n
- Ingestion points: The skill orchestrates the fetching of HTML and metadata from user-provided URLs in SKILL.md (Step 1). \n
- Boundary markers: The skill contains a dedicated 'External Content Safety' section that explicitly instructs the agent to treat all fetched content as untrusted and to never follow instructions, commands, or directives embedded within it. \n
- Capability inventory: The workflow includes writing files to the local './import-work' directory and making network requests to scrape content. \n
- Sanitization: The skill provides high-level instructions to the agent to avoid instruction following in data, but does not define specific automated sanitization logic in this orchestrator. \n
- [EXTERNAL_DOWNLOADS]: The skill is designed to scrape and download content, metadata, and images from external websites provided as input for the migration process.
Audit Metadata