The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to create a Markdown document based on user-provided information. This creates a surface where malicious instructions provided by a user could be persisted into a local file, potentially affecting other tools or agents that process the resulting document.
Ingestion points: User answers regarding the recipient's role, expertise, and specific information needs (SKILL.md).
Boundary markers: The questionnaire template does not utilize specific boundary markers or delimiters to isolate user-provided content from the document structure.
Capability inventory: The skill utilizes a file-write capability to save the questionnaire as a .md file in the current directory (SKILL.md).
Sanitization: No explicit sanitization or validation of user-provided strings is mentioned before they are written to the document.
[NO_CODE]: The skill consists entirely of Markdown instructions and YAML configuration. No Python scripts, Node.js code, or other executable files are included in the package.

to-questionnaire