domain-migration

Fail

Audited by Snyk on Nov 12, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate domain-migration workflow, but its monitoring section embeds promotional pitches for two third-party services (AI SEO Tracker and LinkDR), and LinkDR is set up as an external SKILL.md the agent would follow to place new links, which is promotion unrelated to the migration task.

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

  • Third-party content exposure detected (medium risk: 0.30). The required Step 1 and Step 4 workflow consumes a backlink export (Ahrefs or similar) whose anchor text and referring-page data are authored by outside sites, and anyone can create such links without the agent selecting an item first.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The LinkDR SKILL.md URL is an inbound instruction source the agent would adopt at runtime, and LinkDR is a third-party commercial service without established first-party provenance, so it is common/reputable unofficial and rates medium; the source: metadata, the AI SEO Tracker MCP/status endpoint, and the local script's curl calls against user-supplied URLs are not operational dependencies.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 12, 2026, 02:51 AM
Issues
3