adapt
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process user-provided UI descriptions and target source code to perform 'responsive passes.' * Ingestion points: The skill takes input from user descriptions of UI targets and existing source code files mentioned in the instructions (SKILL.md). * Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed code are present in the skill instructions. * Capability inventory: The skill is explicitly granted authority to 'edit code directly,' which involves file system write operations (SKILL.md). * Sanitization: The instructions do not define any validation or sanitization steps for the external content before it is processed and written to the codebase.
Audit Metadata