paid-ads
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted external sources, which creates a vulnerability surface where malicious instructions could be embedded in those sources to influence the agent.
- Ingestion points: The skill explicitly instructs the agent to read
.claude/product-marketing-context.md(found inSKILL.md) and requests landing page URLs from the user to evaluate products and offers. - Boundary markers: There are no instructions or delimiters provided to tell the agent to ignore or isolate potentially malicious instructions contained within these external files or web pages.
- Capability inventory: The skill utilizes integrations with major ad platforms (Google Ads, Meta, LinkedIn, TikTok) and is capable of generating ad copy, creating campaign structures, and managing budget allocations.
- Sanitization: The skill does not mention any validation, filtering, or sanitization processes for the content ingested from the context files or landing pages.
Audit Metadata