fetch
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the official Browserbase SDKs using
pip install browserbaseandnpm install @browserbasehq/sdk. These packages are associated with the service provider and are standard for this type of integration. - [INDIRECT_PROMPT_INJECTION]: By design, the skill fetches and returns content from external URLs (
response.content). This creates an attack surface where a malicious website could attempt to influence the agent's behavior through embedded instructions. The skill proactively mitigates this with 'Safety Notes' instructing the agent to treat fetched content as untrusted.
Audit Metadata