The Agent Skills Directory

[SAFE]: The skill consists entirely of documentation and instructions related to SEO best practices for robots.txt management. It does not include executable code, scripts, or suspicious commands.
[EXTERNAL_DOWNLOADS]: The skill references technical articles from Vercel and official documentation from Google Search Central. These are well-known, trusted sources in the web development and SEO community and are documented here for transparency.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read project configuration files (e.g., .claude/project-context.md) to determine site settings. This represents a potential indirect prompt injection surface if those external files were to contain malicious instructions.
Ingestion points: .claude/project-context.md and .cursor/project-context.md (referenced in SKILL.md).
Boundary markers: None specified in the instructions.
Capability inventory: No specific restricted tools are defined; the skill utilizes the agent's default capabilities for file reading and reasoning.
Sanitization: No specific sanitization or validation of the ingested context file content is described.

robots-txt