maestro-milestone-audit
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs expected project analysis by reading workflow configuration and source code to identify integration gaps.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests untrusted data from repository files and interpolates it into sub-agent prompts. 1. Ingestion points: .workflow/roadmap.md and .workflow/phases/*/index.json. 2. Boundary markers: Absent. 3. Capability inventory: Bash, Write, and Agent. 4. Sanitization: Absent. As this surface is a byproduct of the skill's primary auditing purpose, it does not represent a malicious finding.
Audit Metadata