Skills
Navigate
skills/scrapfly/skills/scrapfly-extraction/Gen Agent Trust Hub

scrapfly-extraction

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites, creating a surface for indirect prompt injection.
  • Ingestion points: The body parameter in ExtractionConfig (referenced in SKILL.md) allows the agent to ingest arbitrary HTML or markdown content from the web.
  • Boundary markers: The skill documentation does not provide instructions for using delimiters or boundary markers to prevent the agent from executing instructions embedded within the ingested content.
  • Capability inventory: The skill uses client.scrape to fetch web content and client.extract to process it with LLM-based models (defined in SKILL.md), returning the results to the agent.
  • Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the extraction engine.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the scrapfly-sdk Python package, which is the official library associated with the service vendor.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:41 PM