lark-approval

Warn

Audited by Snyk on Oct 18, 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 workflow queries and manages Lark approval tasks and instances via lark-cli, which accesses user-facing approval feeds and tasks containing titles, comments, and form summaries submitted by other participants.

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

  • Direct money access detected (medium risk: 0.30). The skill operates an enterprise workflow and approval management system (Feishu/Lark approvals), which can handle business documents such as leave requests and expense reimbursement claims (SKILL.md:45). Approving or creating reimbursement and leave approvals constitutes indirect financial processing (creating/submitting bills, expenses, or payroll-related claims for downstream handling). Since this is an indirect financial operation, it falls under the indirect operation scope without requiring direct payment control evaluation.

Issues (2)

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 18, 2026, 12:45 PM
Issues
2