outreach-sequence-builder

Warn

Audited by Snyk on Oct 11, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to make a live curl request to https://generativelanguage.googleapis.com using an unverified user-supplied API key, which constitutes an external runtime operational dependency with strong official provenance but involves dynamic execution.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (medium risk: 0.30). The skill generates sales outreach sequences and optionally drafts email touchpoints in Gmail via Composio if a user confirms. Drafting an email draft is an indirect financial/administrative operation (creating bills/invoices/records/drafts). As an indirect operation, it falls under the indirect category (or no financial transaction executed directly). Because no direct financial transfer, charge, or payment instruction is executed, the financial exposure is indirect (or non-transactional drafting), resulting in a medium evaluation.

Issues (2)

W012
MEDIUM

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

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 11, 2026, 06:03 AM
Issues
2