cold-email

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 required "When They Reply" workflow has the agent classify and triage prospect replies, which are outsider-authored free text, and Instantly reply-received webhooks feed that triage without the agent selecting a specific item.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill's GitHub tools registry and integration guides (individual-maintainer repository, unofficial) are pointed to "for setup," which the recall-first rule treats as a plausible instructed setup source, so this is a medium-tier unofficial dependency rather than a clear no.

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 gives concrete, agent-reachable setup guidance (buying secondary domains, configuring SPF/DKIM/DMARC, provisioning mailboxes, and webhook-driven sequence pausing), which is an operational change, but it states no explicit irreversible operational loss, so it fails gate 2 and 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