NYC

ydata-profiling

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill's Streamlit integration accepts arbitrary user-uploaded CSVs via st.file_uploader (and other examples show reading user-provided files like pd.read_csv), meaning the agent ingests untrusted, user-generated third‑party content and will read/interpret it as part of profiling.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:24 AM