responsive-search-ad-writer
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (search terms, keywords, and page content) which serves as an injection surface. 1. Ingestion points: Data from Google Ads MCP or user-pasted text in SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: Restricted to text generation and validation in SKILL.md; no execution tools present. 4. Sanitization: None present.
- [DATA_EXPOSURE]: The skill is configured for read-only access to Google Ads account data via the MCP as defined in skill.meta.json, preventing unauthorized write operations.
Audit Metadata