openclaw-agent-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill exhibits an indirect prompt injection surface (Category 8) because it creates behavior-defining files for other agents based on untrusted user input. 1. Ingestion points: User responses to clarifying questions in
SKILL.md(Workflow Step 1). 2. Boundary markers: Absent; user input is interpolated intoIDENTITY.md,SOUL.md, andAGENTS.mdtemplates without delimiters. 3. Capability inventory: The skill utilizes file system operations (mkdir,touch) and theopenclawCLI, and the resulting agents are intended to have tool-use capabilities. 4. Sanitization: No input validation or escaping is implemented.
Audit Metadata