stably-cli
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests natural language prompts to drive test generation and verification, creating a potential surface for indirect instructions.
- Ingestion points: User prompts passed as arguments to
stably plan,stably create, andstably verifyas described inSKILL.md. - Boundary markers: Absent; inputs are interpolated directly into shell command arguments.
- Capability inventory: The skill possesses file writing/modification capabilities (
stably plan,stably fix,stably create) and shell command execution (stably test) across all referenced files. - Sanitization: The skill instructions do not specify input validation or sanitization, relying on the external CLI tool's internal logic.
- [EXTERNAL_DOWNLOADS]: Fetches the Stably CLI and associated Playwright reporter from the vendor's official distribution channels.
- [DYNAMIC_EXECUTION]: Automatically generates
test.fixme()skeletons and functional Playwright test scripts based on AI-driven analysis of the codebase and user requirements. - [COMMAND_EXECUTION]: Invokes shell commands to perform test execution, environment management, and project initialization tasks.
Audit Metadata