analyze-azdo-build

Warn

Audited by Snyk on Jun 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The required Phase 1 workflow runs Get-AzureDevOpsBuildAnalysis.ps1, which fetches Azure DevOps build timeline/task data (including timeline.records[].issues and failed task error messages) from an external CI system at runtime; those outsider-authored log/error texts are then parsed and included in the agent’s LLM context via the script’s returned fields like ErrorMessages/FailedTests and the rendered “Failure Hierarchy”/summary.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

  • Hidden Unicode characters detected (1 type(s) found)

Issues (2)

W011
MEDIUM

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

W021
MEDIUM

Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 17, 2026, 12:26 AM
Issues
2
Security Audit — snyk — analyze-azdo-build