infsh-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and references explicitly show running web-search/extraction apps (e.g., "infsh app run tavily/search-assistant" in Quick Examples and the "Search" entries in "What's Available" and app-discovery.md), which fetch and return open/public web content that the agent is expected to read and could materially influence subsequent actions, exposing it to untrusted third-party content and indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill’s installation instructs users to run a remote installer that is piped to a shell (curl -fsSL https://cli.inference.sh | sh), which fetches and executes remote code (and additional binaries from dist.inference.sh) and is required to use the CLI-based skill, so it presents a high-risk runtime dependency.