krea-marketing

Warn

Audited by Snyk on Oct 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.70). The skill contains an explicit npx package installation command instructing the agent to fetch external code at runtime from heygen-com/hyperframes, which constitutes an unverifiable runtime external dependency from an unofficial GitHub-owned repository.

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

  • Direct money access detected (medium risk: 0.30). The skill is a creative AI agent for Krea.ai (SKILL.md:10) that generates marketing visuals, ads, storyboards, and content. It optionally interfaces with Meta Ads MCP for performance analysis, account reads, and campaign drafting/activation (SKILL.md:12, 75, SKILL.md:21, 33), where writes are paused by default and live launch/budget changes require explicit approval (SKILL.md:33). This constitutes an indirect financial/campaign operational capability (ad campaign management/activation). As an indirect operation, it is evaluated under the indirect financial scope and does not require direct payment control 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 22, 2026, 08:42 AM
Issues
2