The Agent Skills Directory

[SAFE]: The skill is entirely composed of markdown instructions and reference files providing a CRO analysis framework. No instances of command execution, credential access, or network exfiltration were found.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external landing pages and URLs, which represents a surface for indirect prompt injection. 1. Ingestion points: User-provided URLs and marketing page text (SKILL.md). 2. Boundary markers: Absent; there are no specific instructions to ignore embedded commands in the analyzed content. 3. Capability inventory: No dangerous tools or actions (such as subprocess calls, file writing, or network operations) are utilized by this skill. 4. Sanitization: Absent; however, the structured analysis framework naturally constraints the output to marketing recommendations.

cro