The Agent Skills Directory

[SAFE]: The skill's primary function is to provide a comprehensive 14-dimension framework for reviewing Product Requirement Documents. All dimensions are documented in standard Markdown files.
[COMMAND_EXECUTION]: The script scripts/validate.py utilizes subprocess.run to execute the local scripts/build.py script. This is used for internal validation of the skill's build process and does not involve untrusted or user-supplied input.
[EXTERNAL_DOWNLOADS]: No remote downloads or automated execution of external scripts (e.g., piping curl to bash) were detected in the codebase.
[DATA_EXFILTRATION]: No network calls or unauthorized access to sensitive file paths (such as SSH keys or cloud credentials) were identified. Data processing is confined to the document content provided by the user.
[PROMPT_INJECTION]: The skill uses instructional language to guide the AI's behavior for a specific task. There are no patterns suggesting attempts to bypass safety filters or extract system prompts.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted Product Requirement Documents. However, because the skill does not have access to high-privilege tools (such as network or filesystem write capabilities), the surface area for a successful indirect injection attack to cause system harm is minimal.

check-prd