israeli-accessibility-compliance

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

• Third-party content exposure detected (high risk: 1.00). The skill’s audit workflow and examples (SKILL.md Examples and scripts/audit_a11y.py) explicitly fetch and parse arbitrary public URLs via requests.get and BeautifulSoup to run audits, meaning untrusted third‑party webpage content is ingested and used to drive audit results and remediation decisions, which could enable indirect prompt injection.