The Agent Skills Directory

[SAFE]: No security issues were detected. The skill's primary function is to process existing conversation context and generate a document based on a provided template.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from conversation history to generate a PRD. However, the skill does not use any tools that allow for command execution, file system modification, or network access, which eliminates the risk of an exploitable attack surface.
[EXTERNAL_DOWNLOADS]: The skill references a local dependency discuss-task via a relative file path (../discuss-task/SKILL.md). This is a standard organizational pattern for skill suites and does not involve downloading content from remote or untrusted sources.

to-prd