homepage-info-extractor
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches content from external web pages and search engine results as part of the data extraction workflow.- [COMMAND_EXECUTION]: Employs browser automation via Playwright MCP to navigate websites, intercept resources, and capture content.- [PROMPT_INJECTION]: The skill processes untrusted external data, creating an attack surface for indirect prompt injection.
- Ingestion points: Reads HTML and text from target URLs and search snippets (SKILL.md, Steps 4-6).
- Boundary markers: No delimiters or safety instructions are defined to separate scraped content from agent instructions.
- Capability inventory: Writes extracted information to markdown files in the local results directory.
- Sanitization: No sanitization or filtering of external data before output generation is specified.
Audit Metadata