Skills
Navigate
skills/scrapfly/skills/scrapfly-sdk-go/Gen Agent Trust Hub

scrapfly-sdk-go

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs through the Scrape method and allows for AI-driven data extraction via ExtractionPrompt. This creates a potential surface where malicious instructions embedded in a scraped web page could attempt to influence the agent's behavior.
  • Ingestion points: Untrusted data enters the agent context via the ScrapeConfig.URL field.
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent to ignore instructions found within the scraped content.
  • Capability inventory: The skill possesses network access (via the Scrapfly API) and AI extraction capabilities.
  • Sanitization: The instructions do not detail any sanitization or filtering of the external content before it is passed to the extraction prompt.
  • [SAFE]: All external resources and package installations reference the official vendor infrastructure, including the github.com/scrapfly/go-scrapfly repository and the scrapfly.io website.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 06:46 AM
Security Audit — agent-trust-hub — scrapfly-sdk-go