ads-budget
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze advertising budget and performance data from external platforms.
- Ingestion points: Performance data collection described in the 'Process' section (step 1).
- Boundary markers: The instructions do not define delimiters or protective framing to separate ingested data from agent instructions.
- Capability inventory: The agent identifies campaigns to 'Kill' or 'Scale', providing a path for injected data to influence account management decisions.
- Sanitization: There are no documented checks to validate the integrity of the performance data or filter potential injection strings within metadata fields.
Audit Metadata