devtu-self-evolve

Warn

Audited by Snyk on Mar 8, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's Testing Phase (SKILL.md) and the Researcher Persona template (references/persona-template.md) explicitly instruct launched agents to query and interpret public third-party databases (e.g., CIViC, PubChem, ClinVar, gnomAD, GTEx, FAERS, GWAS catalog), ingesting untrusted external content that is used to generate issue reports and drive fixes, so that third-party content can materially influence subsequent tool use and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 09:09 PM