fetch-rendered
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the Chromium browser engine using the Playwright framework during the setup phase. Playwright is a well-known automation library maintained by Microsoft.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to install Node.js dependencies, manage the lifecycle of a local rendering server (server.js), and perform network requests to the local service using curl.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it fetches and processes content from arbitrary external URLs.
- Ingestion points: Content is ingested from external URLs via the local rendering server (SKILL.md).
- Boundary markers: The skill does not implement specific boundary markers to wrap or isolate the fetched content.
- Capability inventory: The agent has access to the Bash and Read tools, allowing for shell command execution and file reading.
- Sanitization: No evidence of sanitization or filtering of the fetched content is provided in the skill documentation.
Audit Metadata