paid-ads-manager
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which creates a surface for potential instruction injection through the data being analyzed.
- Ingestion points: The skill accepts external inputs including 'Existing creative assets', 'brand guidelines', and 'Current campaign performance data' in the SKILL.md file.
- Boundary markers: There are no specified delimiters or instructions to ignore embedded commands within the provided external ad assets or performance reports.
- Capability inventory: The skill is designed to autonomously manage campaigns, generate creative briefs, and produce performance reports across Meta, LinkedIn, Twitter, and Google.
- Sanitization: No explicit sanitization, filtering, or validation processes for external content are defined in the instructions.
Audit Metadata