The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a surface for indirect prompt injection attacks.
Ingestion points: The skill uses WebFetch to crawl the user's website (homepage, about, services, and landing pages) and WebSearch to monitor for Google Ads policy changes.
Boundary markers: There are no instructions to use delimiters or XML tags to encapsulate the external content, nor are there instructions to ignore instructions embedded within the fetched data.
Capability inventory: The skill has permissions to write structured JSON files to the local filesystem (business-context.json and personas/) and generate audit reports based on this data.
Sanitization: The instructions do not specify any validation, filtering, or sanitization of the fetched web content before it is used to generate personas or business summaries.

ads-audit