google-search-ads-builder
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs and search results during the research phases, which could potentially harbor malicious instructions.
- Ingestion points: Phase 0 (Product URL, Competitor domains), Phase 1B (Competitive Keyword Mining via search results), and tool outputs from
web_searchandfetch_webpage(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are defined for the data fetched from external URLs.
- Capability inventory: The skill possesses the capability to perform network operations (
web_search,fetch_webpage) and write files to the local directoryclients/<client-name>/ads/(SKILL.md). - Sanitization: There are no documented steps for sanitizing or filtering instructions that might be embedded in the HTML or metadata of analyzed competitor sites.
Audit Metadata