page-cro
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions and reference tables for analyzing marketing pages. It does not perform any network operations, execute code, or request sensitive permissions. The reference to local context files follows standard practices for project-aware agents.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for analyzing marketing pages, which acts as a data ingestion surface for untrusted external content. While such content could contain malicious instructions, the skill's focus on specific components (Value Propositions, CTAs, Trust Signals) naturally limits the agent's susceptibility to general instruction overrides.\n
- Ingestion points: Marketing page content (SKILL.md)\n
- Boundary markers: No explicit instructions to ignore embedded commands are included.\n
- Capability inventory: The skill provides logical frameworks; it does not request network access or file-writing permissions.\n
- Sanitization: Content is processed as provided without specific validation or sanitization logic.
Audit Metadata