goldbeater
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API (api.goldbeater.ai) which includes Google Ads audit findings and evidence. This creates an attack surface where external content could theoretically attempt to influence agent behavior. However, the skill's capabilities are limited to read-only tools and it lacks the ability to execute shell commands, write files, or perform arbitrary network operations, which significantly mitigates the risk of such injections having any harmful effect.
Audit Metadata