github-actions-integration

Warn

Audited by Snyk on Jun 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). Issue-to-Fix workflow’unda claude-fix label’ı tetiklenince action, github.event.issue.title ve özellikle github.event.issue.body içeriğini (outsider tarafından yazılmış issue metni) LLM’e direct_prompt üzerinden serbest metin olarak besler.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The workflow uses the external GitHub Action anthropics/claude-code-action (https://github.com/anthropics/claude-code-action referenced as uses: anthropics/claude-code-action@v1), which is fetched and executed at runtime by GitHub Actions and directly controls prompts (direct_prompt) and performs code actions (creating PRs), so it is a required runtime external dependency that executes remote code and controls agent instructions.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 22, 2026, 07:46 AM
Issues
2
Security Audit — snyk — github-actions-integration