multi-asset-morning-briefing

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow requires the agent to read web articles and news sources (such as Reuters, Bloomberg, and local financial news) to supplement market data, exposing it to outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill executes npx to fetch and run remote code from the @nomadamas/k-skill package repository during runtime instruction steps, but package registries are transparent intermediaries and the underlying publisher provenance of the package is unverified and arbitrary third-party content.