The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown documentation, templates, and instructions. There are no scripts, binaries, or executable commands included in the repository.
[SAFE]: Analysis of the instructions and reference materials found no evidence of malicious patterns, data exfiltration, or unauthorized access.
[PROMPT_INJECTION]: The skill processes untrusted external data such as requirement docs and design files (specified in SKILL.md). No boundary markers or sanitization logic are defined for this data. However, the skill possesses no capabilities for subprocess execution, network operations, or file-writing across any of its files, meaning that the surface for indirect prompt injection is limited to affecting the content of the generated documentation itself.

standard-prd