make-paper-collage-video

Warn

Audited by Snyk on Aug 6, 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). Outsider-authored free text is ingested when the workflow runs project:intake at capability-review/intake and records the user’s answers into project.json via the host Ask Question UI or a compact text fallback.

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

  • Direct money access detected (high risk: 1.00). The skill exposes an explicit command to modify an approved image budget cap ("project:increase-image-budget -- --limit=") and references a concrete budget field (budgetDecision.imageAttemptLimit). That is a specific API to change a budget/limit (not just read-only). Under the rules, presence of an API that updates budgets constitutes Direct Financial Execution authority.

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
Aug 6, 2026, 06:21 AM
Issues
2