tavily-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill shows an explicit CLI option tvly login --api-key tvly-YOUR_KEY (and an env var example), which instructs embedding an API key directly into a command or output and therefore requires handling/outputting secret values verbatim.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). The skill instructs users to curl and pipe a shell script from an unknown personal domain (https://cli.tavily.com/install.sh) into bash, which is a high-risk pattern because it executes remote code from an untrusted source.

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

• Third-party content exposure detected (high risk: 0.90). The required workflow uses Tavily commands like tvly search / tvly extract / tvly crawl (runtime web search and content extraction), which will fetch and ingest outsider-authored public web page text into the agent’s LLM-consumed JSON output.

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

• Potentially malicious external URL detected (high risk: 1.00). The README instructs running a remote installer that is fetched and executed via shell (curl -fsSL https://cli.tavily.com/install.sh | bash), which downloads and runs remote code as a required installation step.