iblai-api-agent-memory

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

• Third-party content exposure detected (high risk: 0.70). The required workflow reads and injects agent memory content into the system prompt at runtime (“prepend them to the system prompt as markdown” via the injection/read path), and those memory rows originate from prior user-agent conversation turns (outsider-authored text relative to the operating user) which is therefore eligible for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill documents and example curl call show runtime use of the API at https://api.iblai.app to fetch user/agent memories which are explicitly injected into the agent's system prompt, so this external URL can directly control agent prompts.