odoo-knowledge-agent
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). SKILL.md describes a runtime workflow that scrapes Odoo Forum pages (outsider-authored free text) and then uses that text as input to an LLM via OpenAI chat completions (messages built from scraped thread title/question/answer).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill's runtime scraper fetches content from https://www.odoo.com/forum and injects scraped titles/questions/answers directly into OpenAI prompts (see client.chat.completions.create), so external forum content controls the model input.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata