The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network operations and accesses local environment files to gather context for its audit.
Evidence:
Accesses local files .agents/product-marketing-context.md and .claude/product-marketing-context.md to retrieve business and marketing context.
Uses curl and web_fetch to perform network requests to external domains for the purpose of analyzing site health, robots.txt, and sitemaps.
[PROMPT_INJECTION]: The skill has an inherent vulnerability to indirect prompt injection (Category 8) due to its data ingestion surface.
Ingestion points: External website content and metadata retrieved via web_fetch and curl commands (SKILL.md).
Boundary markers: Absent; there are no instructions to the agent to treat fetched web content as untrusted data or to use specific delimiters to isolate it from instructions.
Capability inventory: The skill utilizes web_fetch and curl for network retrieval and is instructed to perform analysis based on the retrieved data.
Sanitization: Absent; the skill does not specify any validation, filtering, or escaping of the HTML or text content received from external sources before processing.

seo-audit