paid-media-search-query-analyst
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze search term reports and raw query data from external advertising platforms (Google Ads). Since these search queries originate from third-party users on the internet, they represent an untrusted data source that could contain adversarial instructions intended to influence the agent.
- Ingestion points: Search term reports and live query data pulled via API or MCP tools as specified in the 'Tooling & Automation' section of SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the raw search query text.
- Capability inventory: The skill description indicates capabilities to 'Push negative keyword changes' and 'deploy negatives' directly to the advertising account, which involves write-access to a production environment.
- Sanitization: There are no documented procedures for sanitizing, escaping, or validating the search term strings before they are incorporated into the agent's context for analysis.
Audit Metadata