secops-detection-engineering

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

• Third-party content exposure detected (low risk: 0.10). Workflow 2 Step 1 has the agent fetch arbitrary, user-supplied threat blog or CVE URLs (SKILL.md lines 216-217) and feed the extracted article text into TDO generation. The attacker can publish poison but cannot force delivery; the agent must first fetch a specific URL.