to-narration
Warn
Audited by Snyk on Nov 10, 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 required workflow reads cited evidence from arbitrary web sources that the agent must fetch for accuracy checks (SKILL.md line 12), which is outsider-authored content the agent actively selects, so exposure is low; the other inputs (BEATS.md, the approved article, voice sources, and the local review reference) are first-party project files.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata