The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites to conduct SEO audits.
Ingestion points: The skill fetches HTML, metadata, and structured data from user-provided URLs using curl or browser rendering as described in SKILL.md and references/seo-checklist.md.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the fetched HTML content.
Capability inventory: The skill performs network read operations (curl) and generates audit reports based on the findings.
Sanitization: The instructions do not detail any sanitization or escaping mechanisms for the external content before it is processed by the agent.

findable