amazon-ads-create-dsp-campaign
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow depends on reading potentially untrusted data from tool outputs to make decisions about live campaign creation and activation.\n
- Ingestion points: Data is ingested from tool responses in
step1_query_account.md,step2_create_campaign.md, andstep4_query_eligible_tactics.mdto determine targeting parameters.\n - Boundary markers: The instructions lack explicit boundary markers or guidance to treat tool-returned data as untrusted when interpolating it into logic flows.\n
- Capability inventory: The skill has significant write permissions, including creating (
allv1_CreateCampaign,allv1_CreateAdGroup) and activating (allv1_UpdateCampaign,allv1_UpdateAdGroup) advertising entities which involve real financial spend.\n - Sanitization: There is no evidence of sanitization or filtering of the content returned from the Amazon Ads API before it is used to parameterize subsequent high-privilege tool calls.
Audit Metadata