infsh-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly shows running public apps that perform web search and return external results (e.g., "infsh app run tavily/search-assistant" in Quick Examples and notes that the CLI "returns the app output directly" with URLs), meaning the agent will fetch and consume untrusted, third-party web content that can influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's installer uses a pipe-to-sh command ("curl -fsSL https://cli.inference.sh | sh") which fetches and executes remote code (and pulls binaries from https://dist.inference.sh) as a required installation/runtime dependency, so it directly executes external code.