domain-storytelling

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it reads and processes YAML files from the domain-stories/ directory to generate project code. An attacker or malicious file could contain instructions that influence the AI to generate backdoors or insecure code patterns.
  • Ingestion points: Reads all YAML files within the domain-stories/ directory (SKILL.md, Phase A and Phase C).
  • Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the processed YAML files.
  • Capability inventory: The skill has significant project impact as it performs file-write operations to generate a domain layer, including entities, aggregates, and repository interfaces across the codebase.
  • Sanitization: There is no explicit sanitization or validation logic mentioned to ensure the content of the domain stories does not contain executable instructions or malicious prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 03:19 PM