team-builder
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It reads markdown files from local directories and interpolates the content directly into a sub-agent prompt without sanitization or protective delimiters.
- Ingestion points: Local markdown files in
./agents/and~/.claude/agents/. - Boundary markers: Absent; content is directly concatenated in the sub-agent prompt (
{agent file content}\n\nTask: {task description}). - Capability inventory: Spawns general-purpose sub-agents via the Agent tool.
- Sanitization: Absent.
Audit Metadata