authority-ad
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured workflow for creating and auditing speech-led educational advertisements. It includes multiple safety constraints directed at the agent to prevent the invention of credentials, testimonials, or medical outcomes.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied briefs, brand assets, and existing advertisements. While this represents a data ingestion surface, the risk is mitigated by a mandatory human approval step before any production tools are invoked.
- [COMMAND_EXECUTION]: The skill references platform-native tools such as
$media-analysis,$image-batch-runner, and$video-batch-runner. These calls are restricted to an approved workflow and require an explicit approval gate (Step 4: Ask For Approval) before execution. - [SAFE]: No obfuscation, data exfiltration, or persistence mechanisms were detected. The use of non-English characters in the metadata is legitimate descriptive text for different advertisement categories.
Audit Metadata