scrapling

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires installing the scrapling package from PyPI and downloading browser binaries via the scrapling install --force command. It also suggests using official Docker images from GitHub Container Registry (ghcr.io/d4vinci/scrapling). These are standard operations for a browser automation tool and target well-known, trusted registries.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates browser automation and JavaScript execution on remote websites. This is the primary intended purpose of the tool and is controlled by the agent/user through specific scraping commands.
  • [COMMAND_EXECUTION]: The skill provides a CLI interface (scrapling extract) and allows the agent to write and execute Python scripts for complex scraping tasks. These capabilities are within the scope of a developer-oriented scraping framework.
  • [INDIRECT_PROMPT_INJECTION]: As a web scraping tool, this skill ingests untrusted data from the internet into the agent's context. The skill instructions include safety guardrails (e.g., respecting robots.txt, avoiding sensitive data) and the framework returns structured content via its MCP server, which helps mitigate risks associated with processing external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 08:14 PM