vvvv-patching

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to check GitHub links (tebjan/vvvv-skills) on first use, which is a low-risk active fetch of external repository contents rather than monitoring a continuous outsider feed.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to check a remote GitHub repository (https://github.com/tebjan/vvvv-skills) on first use after seven days, constituting a weak/unknown/suspicious runtime operational check.