dogfood
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill navigates to user-provided external URLs and processes their content using
browser_snapshotandbrowser_vision. This creates a surface for indirect prompt injection, where a malicious or compromised website could embed instructions designed to influence the agent's behavior, manipulate the final QA report, or attempt to exploit the agent's file-writing capabilities.
Audit Metadata