testing-for-business-logic-vulnerabilities

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime tests (SKILL.md curl examples and scripts/agent.py) instruct the agent to send HTTP requests to an arbitrary base_url/target endpoints and then read and interpret responses (resp.status_code and resp.text) to decide findings, so untrusted third-party web content can directly influence its actions.