context-driven-development

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow for 'existing codebase detection' and artifact analysis, which represents a surface for indirect prompt injection from files within a project.
  • Ingestion points: Existing project source code, configurations, and documentation files such as product.md and tech-stack.md.
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are documented for the ingestion process.
  • Capability inventory: The skill consists of markdown instructions and architectural guidance; no executable scripts or system-level capabilities are provided in the skill package.
  • Sanitization: The documentation does not specify sanitization, validation, or filtering procedures for the content ingested from the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 03:10 PM