The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and analyze untrusted data from external URLs.
Ingestion points: SKILL.md workflow steps 2 and 3 require the agent to render and inspect HTML/text content from a user-provided URL.
Boundary markers: The instructions do not specify any delimiters or safety headers to separate retrieved web content from the agent's core instructions.
Capability inventory: The skill's primary actions involve writing markdown reports and drafting text. No executable scripts, subprocess calls, or dangerous filesystem operations are defined within the skill files.
Sanitization: The skill lacks any requirement to sanitize or filter the ingested HTML content before the agent processes it for SEO analysis.

seo-onpage