reverse-engineer-rpi

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

• Third-party content exposure detected (high risk: 0.90). The skill expressly fetches and ingests public third‑party content (e.g., shallow-cloning an upstream repo via --upstream-repo in scripts/reverse_engineer_rpi.py and downloading arbitrary sitemaps/URLs via scripts/fetch_url.py and extract_sitemap_paths.sh), then parses that untrusted repo/docs/help output (and binary --help via scripts/capture_cli_help.sh and embedded-archive extraction scripts) to build registries and drive further actions, so untrusted content can materially influence tool behavior and decisions.