survey-synthesis
Warn
Audited by Snyk on Jul 24, 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). SKILL.md describes a subagent that is spawned with “all accumulated materials”; the subagent prompt (prompt.md) ingests free-text fields like accumulated_notes, which are notes extracted from paper-search/paper-research operations and thus are plausibly outsider-authored (i.e., from other authors’ papers), creating indirect prompt-injection risk.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata