clean-data

Warn

Audited by Snyk on Jul 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The required workflow ingests the user-supplied input file path ($ARGUMENTS) and then reads/parses the CSV/Excel/JSON contents (outsider-authored free text from that file) into LLM context via the skill’s runtime processing and reporting (e.g., validation reason text and example transformations).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 17, 2026, 04:10 PM
Issues
1
Security Audit — snyk — clean-data