audit-langfuse-llm

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

• Third-party content exposure detected (low risk: 0.10). The workflow utilizes firecrawl to search and scrape external web pages and documentation, which is low-risk outsider-authored content ingestion.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs execution of npx --yes @playwright/cli@latest and npx langfuse-cli, which invoke third-party packages from public registries without pinned digests or explicit official publisher provenance verification.