The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external research data and user-provided persona information, which is central to its primary UX design purpose. While this creates a data ingestion surface, the skill does not possess capabilities (like code execution, system modifications, or network access) to exploit this surface.
Ingestion points: Instructions in SKILL.md direct the agent to analyze user-provided files such as research data, personas, and analytics, as well as arguments passed via the $ARGUMENTS placeholder.
Boundary markers: The instructions lack specific delimiters or explicit safety warnings to separate untrusted data from system instructions.
Capability inventory: No scripts, external tool definitions, or shell commands are defined in the skill.
Sanitization: No data validation or sanitization logic is present in the markdown body.
[NO_CODE]: The skill consists solely of markdown instructions for the agent and does not include any scripts, executables, or additional configuration files that execute logic.

journey-map