kiro-validate-impl
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to discover and execute arbitrary shell commands found within project configuration files such as package.json, Makefile, and justfile. It specifically runs discovered TEST_COMMANDS, BUILD_COMMANDS, and SMOKE_COMMANDS. Additionally, it executes grep commands to search for sensitive patterns like passwords and API keys within the codebase.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository and conversation history to determine its execution flow, creating a surface for indirect injection.
- Ingestion points: The skill reads project manifest files (package.json, pyproject.toml, etc.), conversation history, and specification files located in the {{KIRO_DIR}}/specs/ directory.
- Boundary markers: No specific delimiters or safety instructions are used to prevent the agent from following malicious instructions that might be embedded in the project files it parses.
- Capability inventory: The skill has the capability to execute shell commands, perform deep file system searches (grep), and launch application artifacts for 'smoke tests'.
- Sanitization: The instructions do not specify any validation or sanitization of the commands extracted from project manifests before execution.
Audit Metadata