workflow-e2e
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external inputs, such as Chrome DevTools recording files and user prompts, to generate test code and guide sub-agent tasks. This ingestion of untrusted data represents an attack surface for indirect prompt injection, where malicious instructions within the inputs could attempt to influence the agent's behavior.
- Ingestion points: User prompts and recording JSON files.
- Boundary markers: The instructions lack explicit delimiters or instructions to treat input as data rather than instructions.
- Capability inventory: The skill can spawn sub-agents, execute local scripts, and perform filesystem writes.
- Sanitization: No explicit data validation or sanitization is mentioned.
- [COMMAND_EXECUTION]: The workflow involves executing local scripts and testing tools. This is a primary function of the skill but grants the agent the ability to execute code in the project environment.
Audit Metadata