The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to analyze external websites using web_fetch and curl, creating an indirect prompt injection surface where malicious instructions on those sites could attempt to influence the agent's audit behavior.
Ingestion points: Content from external URLs (retrieved via web_fetch and curl) and user-provided data such as Screaming Frog exports.
Boundary markers: There are no explicit instructions or delimiters used to isolate the untrusted external data from the agent's internal logic.
Capability inventory: The skill uses network tools (web_fetch, curl) to read data and accesses local project configuration files (e.g., product-marketing.md).
Sanitization: No explicit sanitization or validation of the external content is performed before the agent processes it for analysis.

seo-audit