PromptInjection

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's reconnaissance workflows (e.g., APPLICATION-RECONNAISSANCE-METHODOLOGY.md and the reconnaissance.sh script) explicitly instruct the agent to navigate to arbitrary target URLs and extract DOM, JavaScript, network logs, and download external scripts/pages (browser navigate, browser extract, browser network-logs, wget), so it ingests untrusted public web content that can influence testing actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:39 AM