avast-premium-security-malware-detection

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to analyze public GitHub repositories (repository metadata and file contents in "Step 1: Repository Metadata Check" and "Step 2: Content Analysis") and references GITHUB_TOKEN/VIRUSTOTAL_API_KEY, so it ingests untrusted, user-generated third-party content that can directly influence detection/reporting actions.