The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local configuration files to determine brand voice and site structure, which creates a surface for indirect prompt injection if those project files contain malicious instructions.
Ingestion points: The skill explicitly checks for and reads .claude/project-context.md and .cursor/project-context.md as specified in the Initial Assessment section of SKILL.md.
Boundary markers: No delimiters or instructions are present to ensure the agent ignores or sanitizes potential instructions embedded within the project context data.
Capability inventory: The skill is designed for content generation (copy, link structures, design checklists); no network operations, file writing, or command execution capabilities were identified in the provided file.
Sanitization: The skill lacks any mechanism to validate or sanitize the contents of the ingested project files before processing them.

404-page-generator