The Agent Skills Directory

[SAFE]: The skill instructions and reference materials focus entirely on providing marketing and UX advice. No dangerous command execution, file system modifications, or network activities were found.
[INDIRECT_PROMPT_INJECTION]: The skill is instructed to read local context files like .agents/product-marketing.md to personalize its recommendations. While reading external data is a potential injection vector, the skill's lack of privileged capabilities (such as network access or shell execution) effectively mitigates the risk.

onboarding