technical-blog-writing

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). These domains serve install scripts (cli.inference.sh) and the skill instructs using curl | sh to execute a remote .sh installer — running unreviewed shell scripts from a non-verifiable source is a high-risk distribution vector for malware.

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

• Third-party content exposure detected (high risk: 0.80). The skill's Quick Start explicitly runs "infsh app run exa/search --input ..." to research topics, which indicates the agent will ingest and act on public search/web results (untrusted third-party content) as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's Quick Start explicitly runs a runtime installer that fetches and executes remote code via "curl -fsSL https://cli.inference.sh | sh" (and the skill relies on the resulting infsh CLI to run remote apps), so the external URL https://cli.inference.sh is a runtime remote-code dependency.