Oracle ADK Expert
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md Slackbot integration example shows the agent directly ingesting user-generated Slack messages (user_message = event["text"]) and passing them to agent.execute, meaning untrusted third-party content from Slack can be read/interpreted by the agent and materially influence tool use or subsequent actions.
Audit Metadata