arjun

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly demonstrates embedding an Authorization Bearer token in a command-line header (--headers "Authorization: Bearer TOKEN"), which requires the agent to include secret values verbatim in generated commands/outputs and therefore poses an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md shows it fetches and fuzzes arbitrary public URLs (e.g., "arjun -u https://target.com/api/endpoint" and batch input "-i urls.txt"), meaning it ingests untrusted third-party web content and interprets responses as part of its discovery workflow, which can materially influence subsequent requests and decisions.