executive-dashboard-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a vulnerability surface for indirect prompt injection. * Ingestion points: Processes CSV, Excel, Google Sheets, database results, and JSON/API responses as described in SKILL.md. * Boundary markers: The instructions lack delimiters or "ignore embedded instructions" warnings when handling external data. * Capability inventory: The skill reads workspace files (strategy/brand.md, about/me.md, etc.) and writes to the filesystem (content/platform/drafts/). * Sanitization: No input validation or filtering is defined for the external data sources.
- [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any executable scripts or binaries.
Audit Metadata