oracle-research

Warn

Audited by Snyk on Mar 11, 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 explicitly requires performing WebSearch queries (Quick/Standard/Deep Dive) and checking public GitHub repositories (e.g., https://github.com/oracle-quickstart/oci-ai-blueprints) and then summarizing and using those findings to create recommendations, so the agent will ingest open/public third‑party content that can materially influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 02:18 AM