ascii-art

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 fetch external web pages from ascii.co.uk and other public APIs to search for and display user-selected or arbitrary ASCII art and weather data.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs runtime curl requests to fetch external content from third-party services (asciified.thelicato.io, ascii.co.uk, qrenco.de, wttr.in), whose instructions and content are treated as behavior-selecting configuration or operational content, representing weak/unknown/suspicious operational dependencies.