agency-zhihu-strategist
Warn
Audited by Snyk on Mar 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to "monitor topic pages and trending questions daily" and to "analyze existing expert answers" on Zhihu—public, user-generated third-party content the agent would read and use to drive question selection and answer strategy, enabling indirect prompt injection risks.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata