hdr-dynmeta-docs

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can fetch outsider-authored free text from public GitHub sources (e.g., raw.githubusercontent.com/quietvoid/.../README.md and api.github.com/.../releases/latest), which hdrdocs.py ingests via urllib.request.urlopen() and then prints/returns as LLM-readable text in fetch, search, and section outputs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime Python script fetches remote content (used directly in search/section/fetch/index) from URLs such as https://raw.githubusercontent.com/quietvoid/dovi_tool/main/README.md and https://api.github.com/repos/quietvoid/dovi_tool/releases/latest, and injects that fetched text/JSON into the agent output/context, so external content directly controls the agent's responses.