The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected. The skill's functionality is transparent and aligned with its stated purpose of project planning.
[PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection because it reads external files (feature.md and project.md) and possesses file-writing capabilities (plan.md). However, the overall risk is assessed as safe because the capability is limited to markdown generation and includes a human-in-the-loop approval step.
Ingestion points: Reads feature.md and docs/project.md to identify the tech stack and requirements.
Boundary markers: No specific delimiters or "ignore" instructions are used to encapsulate the content of the ingested files.
Capability inventory: The skill has the capability to write the plan.md file to the local file system.
Sanitization: No sanitization or validation of the ingested content is performed before it is used to generate the plan.

sdd-plan