The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions for product management tasks such as creating personas and mapping user journeys. It does not contain any executable scripts, commands, or remote dependencies.
[PROMPT_INJECTION]: While the skill is designed to process external inputs (such as intake briefs and market reports), it lacks any computational capabilities (subprocess execution, file system modification, or network access) that could be leveraged by an indirect prompt injection attack. The risk is limited to the agent producing incorrect research plans if the input data is malicious.

user-research