skills/grahama1970/agent-skills/code-runner/Snyk

code-runner

Warn

Audited by Snyk on Aug 26, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (medium risk: 0.30). In apply.py::build_file_context, the required workflow reads arbitrary file contents specified by the user/outsider into the LLM prompt (via common.file_bundler.bundle_files over allowlist and read_context).

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Aug 26, 2026, 06:05 PM

Issues

1

Security Audit — snyk — code-runner