research-codebase

Warn

Audited by Snyk on Mar 11, 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.md explicitly instructs the agent to fetch GitHub issue content with gh issue view $ARG --comments, which pulls user-generated, potentially public third-party text that the agent will read and use to understand tasks and drive subsequent actions, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 04:04 AM