data-collection-automation
Warn
Audited by Snyk on Mar 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The ETL pipeline in SKILL.md explicitly includes a "csv_url" branch that calls pd.read_csv(source["url"]) to fetch and ingest arbitrary URLs (third-party web CSVs), which the agent then reads and uses for validation and downstream actions, allowing untrusted external content to influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata