The Agent Skills Directory

NO_CODE (SAFE): The skill consists entirely of Markdown instructions and reference documentation. No scripts, binaries, or configuration files for package managers were detected.
DATA_EXPOSURE (SAFE): The skill mentions reading a local file .claude/product-marketing-context.md to gain product context. This is a standard pattern for providing project-specific information to the agent and does not involve accessing sensitive system credentials or exfiltrating data.
PROMPT_INJECTION (SAFE): All instructions are focused on the primary task of onboarding optimization. No attempts to bypass safety filters or override system instructions were found.

onboarding-cro