ads-report
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues or malicious patterns were detected in the skill instructions. The content consists of natural language guidelines for an agent to process data and generate reports safely.
- [PROMPT_INJECTION]: The skill processes external data ("validated Claude Ads JSON run bundle") and renders it into multiple formats, which is a standard surface for indirect prompt injection. The instructions mitigate this by specifying the use of validated data and deterministic templates.
- Ingestion points: Processes external JSON run bundles (SKILL.md).
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: Rendering HTML/PDF and writing to a local directory (SKILL.md).
- Sanitization: No specific sanitization or escaping instructions are provided.
Audit Metadata