generate-subsystem-skills
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes source code and dependency files across the monorepo to generate new agent instructions and checklists. 1. Ingestion points: Ingests data from subsystem paths defined in subsystem-registry.md (e.g., cli/, server/, rag/). 2. Boundary markers: The prompt templates for sub-agents do not include explicit boundaries or instructions to ignore commands embedded in the analyzed content. 3. Capability inventory: The skill uses Write, Edit, and Bash tools to create and store new instructional content in the .claude/skills/ directory. 4. Sanitization: No explicit sanitization or filtering of analyzed code patterns is performed before generating the new skill files.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute grep commands for code pattern analysis. This usage is restricted to the local monorepo environment and is consistent with the skill's stated purpose of auditing and documenting codebase patterns.
Audit Metadata