hindsight-architect

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime instructions call the Hindsight Cloud API (https://api.hindsight.vectorize.io) to fetch memories/mental-model content that the plan explicitly has the application inject into LLM prompts, so remote content from that URL directly controls agent prompts and is a required dependency.