NYC

csv-data-summarizer

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's analyze.py explicitly calls pd.read_csv on a user-supplied file path and the README/skill docs instruct users to "upload any CSV" to Claude.ai, so the agent will ingest and interpret arbitrary, untrusted user-provided third‑party CSV content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:58 PM