ai-readiness-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow (SKILL.md Step 1–2 and the scripts/audit.sh wrapper) accepts an arbitrary user-supplied URL, sends it to Inlay's API for analysis, and then the agent reads the returned findings and can automatically apply fixes (Step 4 / references/fixes.md), meaning untrusted public website content is ingested and can directly influence actions.