feature-intake

Warn

Audited by Snyk on Jun 26, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The skill explicitly reads existing GitHub issue/project-board state (titles/bodies/comments/fields) via gh issue list ... --json ... projectItems and gh project ... during duplicate/nearby-work checks, and those bodies/comments are outsider-authored free text that can be ingested into the agent’s LLM context for analysis (even though it says to treat them as untrusted).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 26, 2026, 06:15 PM
Issues
1
Security Audit — snyk — feature-intake