paid-media-paid-social-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, including CRM segments, social media campaign performance, and Google Ads conversion data, creating a potential surface for indirect prompt injection.
- Ingestion points: CRM list uploads, social platform APIs, and Google Ads MCP tool outputs (SKILL.md).
- Boundary markers: No delimiters or 'ignore embedded instruction' warnings are included for the data being processed.
- Capability inventory: The skill utilizes Google Ads MCP tools and API integrations for data cross-referencing and budget allocation decisions.
- Sanitization: No explicit validation or sanitization of external data inputs is described in the skill's instructions.
Audit Metadata