scrapegraph
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites which could contain malicious instructions intended to manipulate the agent.\n
- Ingestion points: The
website_url,website_html, andwebsite_markdownparameters across several endpoints (e.g.,smartscraper,crawl,markdownify) fetch or receive content from external sources.\n - Boundary markers: The skill documentation does not specify the use of delimiters or 'ignore' instructions when processing external content.\n
- Capability inventory: The skill uses
orth api runto execute scraping tasks, which can read arbitrary web data and return it to the agent's context.\n - Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the AI.\n- [COMMAND_EXECUTION]: The skill relies on the
orthCLI to communicate with the ScrapeGraph API. This is the primary method of operation and uses the vendor's own infrastructure.
Audit Metadata