agent-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): This skill defines an attack surface by facilitating the creation of subagents that process untrusted user data.
- Ingestion points: Untrusted data enters the agent context via the subagent definitions created in
.claude/agents/orplugins/. - Boundary markers: Absent; the provided templates do not include delimiters or specific instructions to ignore embedded commands within processed data.
- Capability inventory: Template examples explicitly include access to the
Bashtool, enabling potential command execution. - Sanitization: Absent; the skill does not provide any guidance or templates for sanitizing user input before it is processed by the subagents.
Audit Metadata