cro
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external web pages and forms provided by users to perform conversion rate optimization audits. This creates a surface for indirect prompt injection where a malicious webpage could contain instructions designed to override the agent's behavior.
- Ingestion points: Webpage content and form structures retrieved from user-provided URLs as specified in the 'CRO Analysis Framework' in
SKILL.md. - Boundary markers: The skill lacks explicit delimiters or 'ignore embedded instructions' warnings for the data it ingests from external sites.
- Capability inventory: The skill is restricted to text analysis and recommendation generation. It does not use tools for shell execution, file system modification, or non-whitelisted network operations.
- Sanitization: No sanitization or content filtering is implemented for the external data being analyzed.
Audit Metadata