csv-analysis

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). This skill requires automatically analyzing and presenting CSV contents (including sample values, frequent values, and visualizations) with no prompts or redaction, so if a CSV contains API keys/passwords the agent would likely output them verbatim, creating an exfiltration risk.

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests arbitrary user-provided CSV files (see analyze.py which calls pd.read_csv(file_path) and SKILL.md/README instructions like "Upload any CSV file to Claude.ai"), so the agent will read and interpret untrusted third‑party content supplied at runtime.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:25 AM