setup-pipeline

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly passes access tokens and other credentials as command-line arguments and HTTP Authorization headers (e.g., --token "{...}", BAP_TOKEN, Authorization: Bearer {HOST_TOKEN}), which requires the agent to insert and output secret values verbatim — an immediate secret-exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). Phase 1.5 “Ground in current Pipelines documentation” fetches public Microsoft Learn pages at runtime via microsoft_docs_fetch/microsoft_docs_search, and the fetched Learn body text is ingested into the agent context for summarization/comparison (outsider-authored web content).