email-sequences

Fail

Audited by Snyk on Nov 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill's only sign of author interest is a promotional closing line that pitches the author's paid services and community in chat, which is self-serving but disclosed, optional, and gated by role, with no attack on the user.

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

  • Third-party content exposure detected (low risk: 0.10). The cold outbound mode's required per-prospect signal research has the agent search and fetch outsider-authored public content (prospect Google reviews, job boards, ad libraries, news), which it selects itself, so the exposure is low rather than medium.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 17, 2026, 04:01 PM
Issues
2