perplexity-ai

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

• Third-party content exposure detected (low risk: 0.10). The agent interacts with Perplexity AI via ClawLink cli commands to search the web and run completions, which involves processing arbitrary web search results and API content fetched dynamically upon request (low-risk active search/fetch).

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency on an external service (ClawLink) is invoked via npx commands, but without an established first-party organization or verifiable provenance, it is treated as an unknown or weak external dependency.