amazon-ads-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides instructions for tools that ingest untrusted data from Amazon accounts, which could contain hidden malicious instructions.
  • Ingestion points: External data enters the agent context through tools like ask_report_analyst, get_amazon_ads_product_metadata, and list_amazon_ads_campaign_keywords (found in SKILL.md).
  • Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are present to mitigate the risk of the agent following instructions found in the ingested data.
  • Capability inventory: The skill describes tools for listing and analyzing advertising campaigns, keywords, and targets, as well as accessing performance reports (found in SKILL.md).
  • Sanitization: No evidence of sanitization or filtering of the external account content is described in the provided guide.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 01:19 PM