ads-report
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external 'validated versioned report bundles' in JSON format to generate various output types including HTML and PDF.
- Ingestion points: Untrusted JSON run bundles are accepted as the primary input for rendering reports (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts for the processed data.
- Capability inventory: The skill performs rendering of HTML, PDF, and Markdown, which involves interpreting data into potentially executable or layout-sensitive formats (SKILL.md).
- Sanitization: There is no mention of sanitization, escaping, or schema validation for the contents of the JSON bundle prior to rendering.
Audit Metadata