implement-issue

Warn

Audited by Snyk on Jul 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: 0.75). Yes—during the required workflow the skill fetches “issue title, body, … comments, system activity” from an outsider-authored GitHub/GitLab issue via the forge adapter (GitHub gh issue view ... / gh api ... or GitLab glab issue view ... --output json), and that fetched free text is then used in the agent’s LLM context for planning/implementation.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 11, 2026, 05:59 PM
Issues
1