agency-ppc-campaign-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected during analysis of the skill instructions and configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing live data from advertising platforms, which represents a potential attack surface for indirect prompt injection if external data (such as competitor ad copy or campaign metadata) contains malicious instructions.
- Ingestion points: Tooling & Automation section in SKILL.md refers to pulling account_summary, list_campaigns, and auction_insights tools.
- Boundary markers: No specific boundary markers or safety instructions are provided for handling data from these tools.
- Capability inventory: The agent is authorized to execute structural changes such as campaign creation, budget reallocation, and negative keyword deployment.
- Sanitization: The instructions do not specify sanitization or validation of the retrieved account data before processing.
Audit Metadata