sif-to-csv
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes SIF files, which are external data sources. This constitutes an indirect prompt injection surface where maliciously crafted data in fields like 'Product Description' could attempt to influence agent behavior.
- Ingestion points: Reads SIF files from user-specified paths or pasted text (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded in the SIF data.
- Capability inventory: The skill has access to file system tools (Read, Write, Edit, Bash) and Google Sheets integration (SKILL.md).
- Sanitization: Data is parsed based on the SIF specification, but there is no explicit sanitization of text content to prevent prompt injection.
- [DATA_EXFILTRATION]: The skill integrates with Google Sheets to export parsed data.
- Network operations: Uses Google Sheets MCP tools to update spreadsheets.
- Data handled: Product information extracted from user-provided SIF files.
Audit Metadata