web-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to read the API key from a configuration file into a shell variable and then include it inside a JSON payload sent via curl, causing the secret value to be processed and transmitted directly in command output.

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses Tavily search to fetch arbitrary web search results and snippets, placing it at low risk for indirect prompt injection.