project-manager

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for project management tasks such as generating status reports and tracking dependencies using local project metadata.
  • [SAFE]: No network access, credential harvesting, or external downloads are present in the skill configuration or instructions.
  • [SAFE]: The use of emphatic instructional markers (e.g., 'IMPORTANT MUST ATTENTION') is employed to enforce workflow best practices, such as breaking work into tasks via TaskCreate and citing evidence, rather than bypassing security controls.
  • [SAFE]: Data ingestion is limited to internal project artifacts like PBIs and pull requests for report generation, presenting no significant risk of indirect prompt injection exploitation due to the lack of sensitive execution capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 05:50 PM
Security Audit — agent-trust-hub — project-manager