Advanced Reconnaissance

Fail

Audited by Snyk on Mar 9, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). This skill provides step‑by‑step offensive reconnaissance and evasion techniques—DNS brute‑forcing, active subdomain discovery, WAF bypass references, cloud bucket enumeration, and automated/continuous covert monitoring—clearly intended to facilitate unauthorized scanning and attack preparation, indicating high malicious intent.

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs ingesting public, untrusted web content—e.g., certificate transparency sites like crt.sh, Google/GitHub dorks (Layer 2), and crawling/JS extraction of public pages/endpoints (Layer 5)—which the agent would read and use to drive subsequent discovery and tooling decisions.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 9, 2026, 10:07 PM