The Agent Skills Directory

[SAFE]: The skill provides natural language instructions for structuring product documentation. It does not interact with the file system, network, or external APIs.- [NO_CODE]: No scripts, binaries, or executable code are included in this skill. It operates entirely within the LLM's text generation capabilities.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided context to generate documents, creating a theoretical surface for indirect prompt injection. 1. Ingestion points: User conversation context and the optional 'target' argument in SKILL.md. 2. Boundary markers: No explicit delimiters are used to wrap user input. 3. Capability inventory: The skill has no tools, file access, or network capabilities. 4. Sanitization: No sanitization is performed on input context. However, because the skill lacks executable capabilities, this surface presents no functional security risk.

prd