dogfood
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external web applications via browser automation snapshot and console logging commands. This constitutes an attack surface where a malicious website could attempt to influence the agent's behavior via embedded instructions. The skill does not implement specific boundary markers or sanitization logic for the processed web content. However, this risk is considered inherent to the skill's primary function of web exploration and quality assurance.
Audit Metadata