context-driven-development

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides organizational guidelines and templates for project management. It does not include executable code, network operations, or unauthorized file access.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act on documentation from the conductor/ directory. This creates a surface for indirect prompt injection where instructions in those files could manipulate agent behavior. * Ingestion points: product.md, tech-stack.md, workflow.md. * Boundary markers: None. * Capability inventory: File system access for project artifacts. * Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:51 AM