The Agent Skills Directory

[SAFE]: The skill provides strategic instructions and planning templates for website structure. It does not include any code execution, remote downloads, or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill identifies an ingestion surface by instructing the agent to read local project context files to tailor its suggestions. As the skill lacks any dangerous capabilities such as network access or shell execution, this ingestion does not pose a security risk.
Ingestion points: Reads .claude/project-context.md and .cursor/project-context.md (SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present for the read operation.
Capability inventory: None. The skill does not use subprocesses, network tools, or file-writing utilities.
Sanitization: No sanitization or validation of the context file content is defined.

website-structure