reflow
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze and interact with the target application's routes and source code to identify and fix layout issues. This creates a vulnerability surface where malicious directives embedded in the application's content or metadata could influence the agent's actions.
- Ingestion points: The agent is instructed to enumerate all routes and states, and load each view at various dimensions in a browser (SKILL.md).
- Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions found within the application data.
- Capability inventory: The agent is expected to use the shell, edit source files, and use a browser for measurement and screenshots (SKILL.md).
- Sanitization: Absent. No validation or sanitization of the ingested application content is described.
Audit Metadata