The Agent Skills Directory

[SAFE]: The skill instructions are purely advisory, providing frameworks and principles for user onboarding optimization.
[DATA_EXPOSURE]: The skill instructs the agent to check for and read a local context file (.agents/product-marketing-context.md) to personalize its advice. This is a standard practice for context-aware agents and does not involve transmitting sensitive data to external servers.
[INDIRECT_PROMPT_INJECTION]: The skill has a minor vulnerability surface because it ingests untrusted data from the product-marketing-context.md file without explicit boundary markers or sanitization. However, since the skill's capabilities are limited to providing advice and it lacks executable commands or network operations, the risk is negligible.
Ingestion points: .agents/product-marketing-context.md (referenced in SKILL.md under "Initial Assessment").
Boundary markers: Absent; the agent is simply told to "read it before asking questions."
Capability inventory: No subprocess calls, file-write operations, or network requests are present in the skill body or referenced files.
Sanitization: Absent.

onboarding-cro