google-ads-search-terms
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized remote code execution were identified in the provided skill content. The skill operates within expected boundaries for a data analysis tool.
- [DATA_EXPOSURE]: The skill interacts with local files in the
workspace/ads/directory and utilizes thegoogle-ads-mcptool. These operations are consistent with the skill's intended function to analyze ad performance and manage local project state. No sensitive credentials or private system files are accessed. - [COMMAND_EXECUTION]: The skill generates SQL-like queries intended for the
google-ads-mcpsearch tool. These are structured data requests for the Google Ads API and do not constitute arbitrary shell command execution. - [PROMPT_INJECTION]: While the skill ingests external data (search terms from Google Ads), which is a common surface for indirect prompt injection, it lacks high-risk capabilities like arbitrary code execution or network exfiltration that would make such an attack critical. The output is limited to markdown drafts and workspace updates.
Audit Metadata