prd-to-ai-agile-workflow

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not contain any executable scripts, binaries, or automated tool calls.
  • [SAFE]: The skill's instructions are focused on organizational workflow and include explicit 'Privacy Rules' that forbid pushing or submitting anything externally without user approval and require masking private project data.
  • [SAFE]: Although the skill processes external data such as PRDs and branch diffs—which is an inherent surface for indirect prompt injection—it does not request or utilize any high-privilege tools like network access or arbitrary code execution, significantly limiting the potential impact of such an attack. The workflow also emphasizes human review and verification checkpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 02:30 PM
Security Audit — agent-trust-hub — prd-to-ai-agile-workflow