matrix-onboarding

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches documentation from https://matrix-os.com/skills.md, which is an external URL whose content is ingested by the LLM.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill references an external URL (https://matrix-os.com/skills.md) in instructions to fetch current setup instructions if the CLI is missing, presenting a prompt-control/dependency risk.