The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted data from user-supplied URLs. * Ingestion points: Website content, robots.txt, and llms.txt are fetched using WebFetch based on the user-provided URL argument. * Boundary markers: The instructions do not define delimiters or provide guidance to ignore instructions embedded within the fetched content. * Capability inventory: The skill environment includes Read, Grep, Glob, Bash, and WebFetch as defined in the skill manifest. * Sanitization: No sanitization or filtering of the external content is performed before processing.
[DATA_EXFILTRATION]: The skill performs network operations to external, non-whitelisted domains. * Evidence: The skill uses WebFetch to access arbitrary URLs provided by the user to analyze SEO signals and crawler configurations.

seo-geo