excel-variance-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process budget and actual performance data from external Excel files. This creates a potential vector for indirect prompt injection where malicious instructions could be embedded within the spreadsheet data to manipulate the agent's actions.
- Ingestion points: External Excel or compatible spreadsheet data files (referenced in SKILL.md).
- Boundary markers: No specific delimiters or "ignore instructions" directives are included in the skill instructions to help the agent distinguish between data and potentially malicious commands.
- Capability inventory: The skill is granted access to tools including
Bash,Read,Write,Edit,Grep, andGlob(configured in SKILL.md frontmatter). - Sanitization: The instructions do not specify any validation or sanitization routines for the data ingested from external spreadsheet sources.
Audit Metadata