referrals

Warn

Audited by Snyk on Nov 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The review-programs workflow ingests public review text from Trustpilot, G2, Google, and Capterra, which anyone can post to, and reputation triage builds an issue queue from those reviews without requiring the agent to pick a specific item first.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill directs the agent to consult GitHub-hosted tool registry and integration guides "for implementation" and "for configured API access," so that remote content can steer behavior; the repository is individual-owned (coreyhaines31/marketingskills), so it is unofficial and rates medium rather than strong.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill points to configuring referral, affiliate, and review tools (e.g., "Build or configure referral tool" and external integration guides), which could change supporting systems, but it supplies no concrete operation or irreversible loss, so it stays at low.

Issues (3)

W011
MEDIUM

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

W012
MEDIUM

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

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 20, 2026, 09:52 PM
Issues
3