feature-evolution

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted natural language input from users and existing project source code, which creates a surface for indirect prompt injection.\n
  • Ingestion points: User change descriptions and existing functional/technical documents (SKILL.md).\n
  • Boundary markers: The skill incorporates mandatory project context protocols and explicit stop-signs to prevent unauthorized coding tasks (SKILL.md).\n
  • Capability inventory: The skill has permissions to read local code and write Markdown documentation to the filesystem (SKILL.md).\n
  • Sanitization: No validation or sanitization is performed on user-provided descriptions or ingested code files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 10:10 AM