pp-medium-reader

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text can enter the LLM context via the CLI’s runtime ingestion of Medium public surfaces (e.g., read <url|id> fetching an article page/body or search/feed fetching RSS/GraphQL results), which the agent then passes back as JSON/Markdown into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's prerequisites explicitly instruct installing and running remote code (via npx -y @mvanhorn/printing-press-library install medium-reader and go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/medium-reader/cmd/medium-reader-pp-cli@latest), which fetches and executes remote packages that the skill requires to function.