google-ads-audit

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs its stated purpose of auditing Google Ads accounts without any detected malicious patterns or unsafe practices.- [DATA_EXPOSURE]: Although the skill accesses account-level advertising data, it does so using authorized tools provided by the vendor (Cogny AI) and does not exhibit any exfiltration behavior to unauthorized external domains.- [PROMPT_INJECTION]: The instructions follow standard operational logic and do not attempt to bypass safety guidelines or override agent constraints.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (Google Ads reports, search terms).
  • Ingestion points: GAQL query results from various campaigns and search term views defined in SKILL.md.
  • Boundary markers: None explicitly mentioned, but data is handled within structured queries and reporting templates.
  • Capability inventory: Limited to reading Google Ads data and generating internal findings via mcp__cogny__create_finding.
  • Sanitization: Standard data processing is performed; while no specific sanitization of external search terms is described, the risk is minimal given the reporting-focused capability set.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 03:46 PM
Security Audit — agent-trust-hub — google-ads-audit