ad-campaign-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it is designed to ingest and process external advertising campaign data.
- Ingestion points: Campaign performance data is ingested through CSV exports, pasted tables, or screenshots from platforms like Google Ads, Meta Ads Manager, and LinkedIn Campaign Manager, as described in Phase 0 and Phase 1.
- Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate the ingested data from the agent's logic, nor do they include warnings for the agent to ignore instructions that might be embedded within data fields such as campaign names or ad copy.
- Capability inventory: The skill instructs the agent to generate a markdown report and save it to a specific local file path:
clients/<client-name>/ads/campaign-analysis-[YYYY-MM-DD].md. - Sanitization: There is no evidence of data sanitization or validation of the input metrics and labels before they are used to generate the final report.
Audit Metadata