create-agent
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided agent responsibilities into prompts for the agent-author subagent.
- Ingestion points: User-defined agent names and roles in Step 1 of SKILL.md.
- Boundary markers: No delimiters or safety instructions are used to isolate user input in the delegation prompt in Step 2.
- Capability inventory: The agent-author subagent has access to Write and Bash tools to generate and modify files.
- Sanitization: Validation in Step 4 is limited to metadata checks and does not verify the content of the generated agent instructions.
- [COMMAND_EXECUTION]: The workflow involves shell operations to move scaffolded files to final project paths using the Bash tool.
Audit Metadata