zapret-openwrt-guide

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

• Third-party content exposure detected (high risk: 0.90). The skill's updater and diagnostics scripts explicitly fetch and ingest public web content—e.g., update-pkg.sh downloads release metadata and ZIPs from GitHub (https://raw.githubusercontent.com/.../releases and GitHub URLs) and dwc.sh downloads test datasets from hyperion-cs.github.io/dpi-checkers—so untrusted third‑party content is read and can change update/diagnostic behavior and subsequent actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). Flagged because the skill repeatedly documents and instructs editing system-level files, service scripts (init.d/procd), custom.d hooks, configs under /etc and /opt and updating/installing packages — actions that modify the machine state and typically require root privileges.