spawn-planning-agents
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists solely of markdown documentation and workflow instructions. It does not contain any executable scripts, binaries, or direct system configurations.
- [PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection because it orchestrates the analysis of external data that may contain malicious instructions. * Ingestion points: The subagents mentioned, such as codebase-analyzer and thoughts-analyzer, are designed to read files and research documentation from the environment. * Boundary markers: The example prompts provided do not include delimiters or instructions to ignore embedded commands within the analyzed content. * Capability inventory: The skill itself focuses on orchestration and information gathering; it does not directly perform file system writes or network operations. * Sanitization: No sanitization or validation of the ingested codebase content is specified in the planning workflow.
Audit Metadata