jules-implement
Warn
Audited by Snyk on Jun 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s REQUIRED workflow performs “Delta-Based Autoresearch” by doing web/paper searches at runtime for newer articles/papers, and the fetched page/article text is then ingested into the agent’s LLM context as free-form outsider-authored prose.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata