agent-tools

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow is the CLI invocation path (infsh app run … --input …) which ingests user-supplied JSON prompts/strings you provide, but it does not describe any required monitoring/reading of outsider-authored external feeds (e.g., emails, chat, issues, tickets) without you selecting an app and providing input.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs running a shell installer that fetches and executes remote code via "curl -fsSL https://cli.inference.sh | sh", so https://cli.inference.sh is a runtime dependency that executes remote code.