work-tracking

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

• Third-party content exposure detected (high risk: 0.90). The README.md Quick Start explicitly instructs the agent to fetch files from a public GitHub URL (https://github.com/mohammed-io/agentic-ai-tools/...), meaning the agent would ingest open/public third‑party content (a public repo) as part of its workflow, exposing it to potential indirect prompt injection.