draft-cli

Warn

Audited by Snyk on Apr 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly reads user-generated public comments from the hosted Draft service (see "Hosted Read Pattern for Public Page Comments" and commands like draft public-comments list --url 'https://draft.innosage.co/#/preview/<page_id>?mode=static' in SKILL.md), and those comments are used by the agent to guide edits/patches, so untrusted third‑party content could materially influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 06:39 AM
Issues
1