fetch-url

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly demonstrates and recommends passing auth tokens/cookies via the --header CLI flag (e.g., Authorization: Bearer tok_xxx), which encourages embedding secret values directly into generated commands/outputs and thus risks exfiltration.

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

• Third-party content exposure detected (high risk: 1.00). This skill's SKILL.md describes a fetch-url command that fetches arbitrary public web pages (e.g., examples like https://react.dev/... or any ) and returns their content as Markdown for summarization/analysis, so the agent will ingest untrusted third-party web content that can materially influence decisions or follow-up actions and enable indirect prompt injection.