scrapling

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the scrapling package from the official Python Package Index (PyPI), which is a legitimate library for web scraping tasks.
  • [COMMAND_EXECUTION]: The skill executes local CLI commands via a PowerShell wrapper script to perform content extraction. This behavior is restricted to the intended scraping functionality.
  • [DATA_EXFILTRATION]: Network operations are limited to the target URLs provided for scraping. No unauthorized data transmission or sensitive file access was identified.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted web content from external URLs.
  • Ingestion points: Target URLs processed by scrapling extract as described in SKILL.md.
  • Boundary markers: No explicit delimiters or warnings to ignore instructions within the scraped content are defined in the skill instructions.
  • Capability inventory: The skill uses scripts/scrapling.ps1 to execute shell commands and write scraped content to the local filesystem.
  • Sanitization: No sanitization or escaping of the ingested web content is performed before it is made available to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 02:49 PM