smart-weather
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and README explicitly instruct the agent to fetch and parse weather data from the public wttr.in API (e.g., curl "wttr.in/{城市名}"), so it ingests third-party web content that the agent reads and uses to drive clothing/commute decisions—exposing it to untrusted external content that could alter behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata