cro
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze marketing pages via URLs provided by the user. This creates an attack surface for indirect prompt injection if a target website contains malicious instructions intended to manipulate the agent's behavior.
- Ingestion points: Target URLs provided by the user in the prompt.
- Boundary markers: None explicitly defined in the skill for external content.
- Capability inventory: No dangerous tools or commands (such as file writes or shell execution) are requested.
- Sanitization: Relies on the host platform's native safety and sanitization filters.
Audit Metadata