scrapling

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill initiates downloads of external browser binaries (Playwright Chromium) via the scrapling install command and depends on third-party Python packages like scrapling and cairosvg from public registries.
  • [COMMAND_EXECUTION]: The skill includes CLI utilities and scripts (scrapling_scrape.py) that execute system commands for web extraction and allow arbitrary JavaScript execution within the browser context through the execute_js parameter.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the web which could contain hidden instructions targeting the LLM.
  • Ingestion points: Data fetched from URLs via Fetcher, DynamicFetcher, StealthyFetcher, and Spider classes.
  • Boundary markers: None identified; the skill returns raw or filtered page content without explicit delimiters or safety warnings for the agent.
  • Capability inventory: Network access for web crawling, local file system writes for data extraction and checkpoints, and browser-level JavaScript execution.
  • Sanitization: No documented sanitization or filtering of external content to prevent instructional override before the data is passed to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:59 AM