The Agent Skills Directory

[SAFE]: The skill is purely informational and consists of best practices for form layout, field optimization, and user experience. No malicious code or dangerous commands were identified.
[PROMPT_INJECTION]: The skill instructions include a step to read local project context files (e.g., .agents/product-marketing-context.md). This represents a surface for indirect prompt injection; however, because the skill's capabilities are limited to generating text recommendations and do not involve shell execution or network operations, the risk is negligible.
Ingestion points: .agents/product-marketing-context.md (referenced in SKILL.md)
Boundary markers: Absent
Capability inventory: None (the skill provides text-based audit recommendations only)
Sanitization: Absent

form-cro