google-ads-search-term-mining
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it requires the agent to process and classify raw search terms gathered from external Google Ads reports.
- Ingestion points: External Google Ads search term reports pulled via UI, Editor, or API (SKILL.md).
- Boundary markers: None specified; the agent is instructed to read and classify the raw queries directly.
- Capability inventory: The skill primarily outputs analysis, ad copy recommendations, and structural suggestions; it does not contain direct file-write or subprocess execution capabilities.
- Sanitization: No sanitization or filtering of the search query strings is defined before processing.
Audit Metadata