cli

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

• Potentially malicious external URL detected (high risk: 0.80). The saas-create-architecture skill explicitly instructs the agent at runtime to fetch and "Read the complete tool reference" from https://github.com/Melvynx/aiblueprint/blob/main/ai-coding/tools.md and to "Use as primary source" for recommendations, meaning external content from that URL will directly influence the agent's prompts/instructions and outputs.