pp-atlas-obscura

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path invokes atlas-obscura-pp-cli to fetch Atlas Obscura place detail pages (“Community-sourced from atlasobscura.com”), and the CLI’s JSON/provenance output is then ingested into the agent’s LLM context—i.e., outsider-authored free text from public web pages.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running installers that fetch and execute remote code at runtime—e.g. "npx -y @mvanhorn/printing-press-library install atlas-obscura --cli-only" and "go install github.com/mvanhorn/printing-press-library/library/travel/atlas-obscura/cmd/atlas-obscura-pp-cli@latest"—to obtain the required CLI, so external content would be executed during setup.