page-cro
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions and reference material. It does not include any scripts, external tool calls, or requests for sensitive system files. The access to project-specific context in .claude/ is standard practice for identifying relevant business goals.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze marketing content, which serves as a potential ingestion point for indirect prompt injection. However, this risk is managed by the skill's lack of dangerous capabilities.\n
- Ingestion points: Marketing copy, headlines, and page layouts provided to the agent for CRO analysis (SKILL.md).\n
- Boundary markers: None identified in the skill instructions to separate analyzed content from the agent's internal instructions.\n
- Capability inventory: No command execution, network requests, file writing, or other sensitive tool operations are defined within the skill files.\n
- Sanitization: The skill does not include any instructions for sanitizing or validating external content before analysis.
Audit Metadata