Paid Media Auditor
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external advertising platforms and competitive research which serves as a potential vector for indirect prompt injection.
- Ingestion points: The skill uses
WebFetchandWebSearchto retrieve campaign settings, auction insights, creative assets, and landing page content from external advertising environments and websites. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the ad data or landing pages being audited.
- Capability inventory: The agent has access to
Bash,Write,Edit, andWebFetchtools, providing a surface for command execution or file modification if manipulated by external data. - Sanitization: There is no evidence of sanitization or validation logic to filter out instructional content from the retrieved ad account data.
Audit Metadata