cli-anything-agent-native-software

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly supports browsing/installing community CLIs from the public CLI‑Hub and external package sources (see "CLI Hub" commands like cli-hub list/search/install and the "Publishing to CLI‑Hub" / registry.json instructions) and agents are expected to discover and parse SKILL.md from those installed third‑party packages, so untrusted community content can directly influence agent actions.