paid-search-advertising
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as search terms, keyword research data, and landing page content, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Untrusted data enters the agent's context through search term reports, keyword research exports, and landing page analysis fetched from live accounts and external tools (SKILL.md, references/search-build-specification.md).
- Boundary markers: The instructions include clear safety boundaries, specifying that analysis is "read-only" and that any publishing or budget changes require "explicit, action-specific client authority" (SKILL.md).
- Capability inventory: The skill produces ad copy assets (RSA), build specifications, and audit reports. It utilizes other skills for copy generation and tracking planning (SKILL.md).
- Sanitization: The skill does not explicitly define sanitization or escaping protocols for the external content before it is processed or interpolated into prompts.
Audit Metadata