data-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided data from attachments or pastes. Ingestion points: Processes data from attachments or pasted text described in the workflow in SKILL.md. Boundary markers: No specific boundary markers or instructions to ignore embedded instructions in the source data are provided. Capability inventory: Utilizes internal spreadsheet tools for workbook creation as described in SKILL.md; no arbitrary shell execution or external network capabilities are referenced. Sanitization: No explicit sanitization or validation of the input data is described.
- [NO_CODE]: The skill consists solely of natural language instructions and does not include any scripts or executable code.
- [SAFE]: No malicious patterns, obfuscation, or dangerous execution capabilities were detected in the skill instructions.
Audit Metadata