typo3-docs

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow starts by running extraction (scripts/extract-all.sh / scripts/analyze-docs.sh) and the extraction/reference docs explicitly show fetching public repository data via the GitHub API (e.g., "Repository Metadata Extraction" with gh api commands) and ingesting README/CHANGELOG content, so the agent is expected to read untrusted, user-generated web content that can influence analysis and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime "docker run" render step that pulls and executes an external container image (ghcr.io/typo3-documentation/render-guides:latest), which downloads and runs remote code required for rendering, so it is a runtime external dependency that executes remote code.