dag-graph-builder
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted natural language task descriptions to generate executable workflows and is authorized to use multiple file-manipulation and system tools.\n
- Ingestion points: Natural language task descriptions provided by the user (found in
SKILL.md).\n - Boundary markers: The instructions lack explicit markers, delimiters, or 'ignore' warnings for the input processing logic.\n
- Capability inventory: The skill is permitted to use
Read,Write,Edit,Glob,Grep,Task, andTodoWritetools (found inSKILL.md).\n - Sanitization: No input validation or sanitization mechanisms are described for the processed text descriptions.
Audit Metadata