create-agent-template
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill acts as a template generator that processes user-provided agent descriptions and configurations. This architecture creates an inherent surface for indirect prompt injection, where malicious input could influence the logic of the generated automation pipelines.
- Ingestion points: User instructions defining the agent's purpose, inputs, and configuration parameters (SKILL.md).
- Boundary markers: No delimiters or instructions to ignore embedded commands are present in the generated pipeline YAML templates.
- Capability inventory: The generated pipelines in
references/agent-examples.mdandSKILL.mddemonstrate capabilities for shell script execution (shell: bash) and the use of containerized plugins with environment variable access. - Sanitization: The skill does not describe or implement validation or sanitization of user-provided strings before they are interpolated into the generated shell scripts or YAML structure.
Audit Metadata