auto-hypothesis-test
Warn
Audited by Snyk on Nov 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow reads a user-specified data file (CSV/TSV/Excel/JSON), and survey or form exports in that file could contain outsider-written categorical labels that the script echoes back into the LLM context via group names and contingency tables, but the agent must be pointed at a specific file and the attacker cannot push text into a queue the workflow monitors.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata