pp-atlas-obscura

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow executes the atlas-obscura-pp-cli commands (e.g., places, near, route, gaps, surprise) in --agent mode, which fetches/reads third-party place detail content from atlasobscura.com and returns it for the agent to parse without any step that constrains the content to a specific known item.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite/install steps instruct fetching and executing remote code (e.g., "go install github.com/mvanhorn/printing-press-library/library/travel/atlas-obscura/cmd/atlas-obscura-pp-cli@latest" and "go install github.com/mvanhorn/printing-press-library/library/travel/atlas-obscura/cmd/atlas-obscura-pp-mcp@latest"), and the CLI installed by those commands is required for the skill to run.