health
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill performs runtime script generation and execution by interpolating command outputs into JavaScript templates, which are then processed by the
bun -ecommand to calculate composite health scores.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and parses stdout/stderr from external tools (type checkers, linters, test runners), creating a surface where malicious project content could potentially influence the agent. The skill mitigates this risk for critical actions by requiring specific 'tune:' markers in direct user messages to authorize configuration changes (file: SKILL.md).\n- [COMMAND_EXECUTION]: The skill executes multiple command-line utilities, including both standard project tools (e.g.,tsc,shellcheck,bun test) and specialized binaries from the vendor's local environment (located in~/.claude/skills/gstack/bin/).
Audit Metadata