localstack
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
lstkcommand-line tool to manage the LocalStack emulator, including operations to start, stop, restart, and reset the environment. It also referencesdockerrequirements andcurlfor checking the local service health. - [EXTERNAL_DOWNLOADS]: The instructions guide users to install the
lstkCLI through official channels: Homebrew (localstack/tap/lstk), NPM (@localstack/lstk), and the legacy CLI via Pip (localstack). All referenced packages are official vendor resources. - [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it involves reading and processing external data.
- Ingestion points: The agent is instructed to read output from
lstk logsandlstk status(SKILL.md). - Boundary markers: None are explicitly mentioned in the instructions for isolating log content.
- Capability inventory: The skill provides capabilities to execute shell commands, manage local volumes, and handle authentication tokens (SKILL.md).
- Sanitization: There are no instructions for sanitizing or escaping the log output before the agent processes it.
Audit Metadata