The Agent Skills Directory

[SAFE]: No security issues detected across the analyzed files. The skill focuses on providing strategic advice for in-product conversion rate optimization.
[DATA_EXPOSURE]: The skill instructs the agent to read local context files (such as .agents/product-marketing.md) if they exist. This is a standard pattern for establishing project-specific context and does not involve unauthorized data access or exfiltration.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted product marketing context from local files, it lacks any dangerous capabilities (like shell execution, file writing, or network operations) that could be exploited via indirect injection. The analysis of the instructions confirms the agent is used only for generating recommendations.

paywalls