scrape
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for interacting with multiple third-party scraping and brand data APIs using the vendor's 'orth' CLI tool. All operations described are consistent with legitimate data extraction and browser automation use cases.
- [PROMPT_INJECTION]: As a scraping utility, the skill inherently processes content from untrusted external URLs, which represents a surface for indirect prompt injection.
- Ingestion points: Multiple APIs (Scrapegraph, Olostep, Riveter, Brand.dev, Notte) ingest data from arbitrary URLs provided at runtime.
- Boundary markers: The skill does not explicitly define markers or 'ignore' instructions for the agent when processing scraped text, which is typical for documentation-focused skills.
- Capability inventory: The skill allows for network access (via APIs), browser interaction, and structured data extraction, providing the necessary tools for complex web-based tasks.
- Sanitization: No explicit sanitization of retrieved HTML or text content is described in the provided examples.
Audit Metadata