The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown-based instructions, templates, and examples. It does not contain any executable scripts (e.g., Python, JavaScript, Bash) or binary files.
[SAFE]: No security issues were detected across the analyzed files. The skill does not request sensitive file access, perform network operations, or hardcode credentials. It orchestrates activity by referencing other internal skill paths within the repository rather than external or untrusted sources.
[SAFE]: The workflow involves processing user-provided information such as discovery notes and chat history to populate a PRD. While this constitutes an input surface for potential indirect prompt injection, the skill lacks any capabilities (such as code execution or external data transmission) that would allow for an exploit to manifest, rendering the attack surface non-risky.

prd-development