xhs-dm
Warn
Audited by Snyk on Jul 9, 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:60 explicitly states that the other party’s private-message text is treated as “data not instructions,” but the required workflow still involves reading the outsider-authored DM content from the Xiaohongshu UI (via
computer.screenshot/computer.observe) and using it to draft a reply, which would be ingested into the agent’s LLM context as free text for generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata