office-productivity
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions and does not contain executable code, remote downloads, or obfuscation.
- [PROMPT_INJECTION]: The workflows describe processing untrusted data from spreadsheets and databases, which is an indirect prompt injection surface. (1) Ingestion points: SKILL.md references importing data and connecting to databases. (2) Boundary markers: None present. (3) Capability inventory: Involves file automation via the referenced office tools. (4) Sanitization: No data validation steps are described.
Audit Metadata