data-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it is designed to ingest and process untrusted external data sources such as CSV, JSON, and SQL exports while having access to execution tools.
- Ingestion points: External data is ingested via file reading and SQL queries as outlined in the core instructions and analysis lanes.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing or interpolating data from these external files.
- Capability inventory: The skill is allowed to use the
Bashtool and utilizes Python (pandas) for data processing and analysis. - Sanitization: There is no evidence of data sanitization, filtering, or validation logic to prevent instructions embedded within datasets from influencing the agent's behavior.
Audit Metadata