The Agent Skills Directory

[SAFE]: The skill provides legitimate SEO optimization guidelines and code snippets for common web servers (Nginx, Apache) and frameworks (Next.js). The instructions are consistent with industry standards for web performance and search engine optimization.
[EXTERNAL_DOWNLOADS]: The skill references external documentation from well-known sources, including Google Search Central and frontendchecklist.io. These references are used appropriately to support the technical implementation of freshness signals.
[DATA_EXFILTRATION]: No evidence of sensitive data access or unauthorized exfiltration was found. The skill operates on public-facing metadata and HTTP headers that are intended for consumption by search engine crawlers.
[REMOTE_CODE_EXECUTION]: The skill does not contain any patterns for downloading or executing remote scripts, nor does it use dynamic code execution functions like eval() or exec().
[PROMPT_INJECTION]: The skill instructs the agent to audit external content (web pages), which is a potential ingestion point for indirect prompt injection. However, the skill does not define or use high-privilege capabilities that could be exploited, and the risk is considered negligible within this context.
Ingestion points: Content pages and article JSON-LD during audit tasks.
Boundary markers: None specified in the instructions.
Capability inventory: No file-system writes, network operations to unknown domains, or subprocess calls are requested by the skill.
Sanitization: Not applicable as no data is processed by local scripts.

freshness