odoo-knowledge-agent

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly scrapes and ingests solved threads from the public Odoo forum (https://www.odoo.com/forum), which is user-generated/untrusted content that the agent parses and uses to generate guardrails and auto-fixes, creating a clear path for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill scrapes runtime content from https://www.odoo.com/forum and injects the fetched thread titles/questions/answers directly into the OpenAI chat prompts to drive pattern extraction, so this external URL is used at runtime, directly controls model prompts, and is a required dependency.