paid-ads
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential attack surface.
- Ingestion points: The skill is instructed to read local marketing context files (e.g.,
.agents/product-marketing-context.md) and process user-provided landing page URLs. - Boundary markers: There are no explicit instructions to use delimiters or ignore instructions that might be embedded within the ingested context files or the content of landing pages.
- Capability inventory: The skill is designed to work with integrated tools for major ad platforms (Google Ads, Meta, etc.), which could potentially be manipulated if the agent follows instructions found in external data.
- Sanitization: The instructions do not define methods for sanitizing, filtering, or validating the external content before it is used to inform campaign strategies.
Audit Metadata