web-scraper
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process untrusted data from external websites, creating a surface for indirect prompt injection.
- Ingestion points: External data enters the agent's context through HTTP requests (
requests.get) and browser automation (playwright.chromium.launch,page.goto) as described in the Core Capabilities and templates inSKILL.md. - Boundary markers: The skill does not explicitly define boundary markers or 'ignore embedded instructions' prompts when processing scraped content.
- Capability inventory: The skill possesses capabilities to execute network operations, automate browser actions, and parse DOM structures using
BeautifulSoupandplaywright(referenced inSKILL.md). - Sanitization: There are no specific instructions for sanitizing or filtering extracted text before it is presented to the agent for structured data extraction or analysis.
Audit Metadata