The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown instructions and formatting guidelines for a language model to assist in writing business documentation. There are no scripts, command-line operations, or network requests included in the skill definition.- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting external product context to generate requirements documents. While this constitutes an input surface, the skill does not possess any capabilities (such as file system writes, network access, or shell execution) that could be exploited by malicious content within the processed data. Evidence: Ingestion occurs from 'supplied material' (SKILL.md); no boundary markers or sanitization logic are defined; the capability inventory is empty as no tools or scripts are present.

brd-writer