e2e-ci-debug
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's download-artifacts.sh fetches GitHub Actions artifacts (playwright reports, junit.xml, screenshots/traces/videos) from PR workflow runs via the gh CLI, and parse-junit.py explicitly exposes and instructs AI models to read those artifact files (absolute screenshot/trace paths) — meaning the agent will ingest and interpret potentially untrusted, user-generated content from third-party PRs/artifacts.
Audit Metadata