brand-visual-generator
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from external context files (.claude/product-marketing-context.md and .cursor/product-marketing-context.md).
- Ingestion points: SKILL.md references these files in the 'Initial Assessment' section to extract brand identity information.
- Boundary markers: Absent; the skill does not provide delimiters or instructions to ignore potential commands embedded in the marketing context files.
- Capability inventory: Limited to generating design specifications and text-based brand guidelines; no file-system modification or network capabilities are identified within the skill's logic.
- Sanitization: No sanitization or validation of the ingested context data is performed before processing.
Audit Metadata