exploratory-data-analysis
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted scientific data files.
- Ingestion points: Scientific data is read from local files in
scripts/eda_analyzer.pyusing libraries likepandas,Biopython, andh5py. - Boundary markers: The skill lacks delimiters or instructions to the agent to isolate content from these files, allowing potentially malicious text in headers or data fields to influence the agent's behavior.
- Capability inventory: The skill possesses file-read and file-write capabilities via the
eda_analyzer.pyscript. - Sanitization: Extracted metadata and data values are not sanitized before inclusion in the generated reports.
- [DATA_EXFILTRATION]: The skill is designed to read and summarize local file contents for analysis. While this is the intended functionality, it creates an opportunity for the exposure of sensitive information if the agent is directed to analyze non-scientific files such as configuration or credential files that match or bypass its extension-based detection.
Audit Metadata