tabular-eda-review
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze external CSV datasets, which constitutes an indirect prompt injection surface. Maliciously crafted data within these files could potentially influence agent behavior during the analysis workflow.
- Ingestion points: External CSV files and dataset facts loaded from memory sources like Serena or the
docs/memory-bank/directory. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of the data files.
- Capability inventory: The skill uses standard shell and editor tools, and references a local utility script (
scripts/export-gemini-skill.py) for skill management. - Sanitization: There are no explicit instructions to sanitize, validate, or escape content read from the datasets before the agent processes them.
Audit Metadata