skill-craft-review

Warn

Audited by Snyk on Jul 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow instructs the runtime reviewer agent to “Read the whole submission” including supporting files for the plugin (and also to open review-checklist.md), meaning the agent will ingest the OUTSIDER-authored submission text it is asked to review as readable prompt context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 22, 2026, 04:49 PM
Issues
1
Security Audit — snyk — skill-craft-review