paid-media-search-query-analyst

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection attack surface identified. The skill is designed to ingest and process search term reports from external accounts, which could contain adversarial content.
  • Ingestion points: Search term reports pulled via Google Ads API or MCP tools (documented in SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded commands within the search query data.
  • Capability inventory: The skill specifies capabilities for pulling data and pushing keyword modifications back to live accounts (documented in SKILL.md).
  • Sanitization: No explicit sanitization or validation of the search query text is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 02:24 AM
Security Audit — agent-trust-hub — paid-media-search-query-analyst