The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because its core function involves processing untrusted content from external websites.
Ingestion points: The skill instructions specify using web_fetch and curl to retrieve the content of URLs provided by the user for auditing purposes (SKILL.md).
Boundary markers: The instructions lack explicit boundary markers or directives for the agent to treat fetched content strictly as data and to ignore any natural language instructions that might be embedded in the HTML or metadata of the audited sites.
Capability inventory: Across the provided files, the skill's capabilities are limited to analysis and reporting. It does not perform subprocess calls, file-write operations, or secondary network requests triggered by the data being processed.
Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external URLs before it is processed by the agent.

seo-audit