boxlang-runtime-cli-scripting
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents methods for ingesting untrusted data from external sources.
- Ingestion points: Data enters the agent's context through
CLIGetArgs(),CLIRead(), and theserver.cli.parsedscope as described inSKILL.md. - Boundary markers: The instructions do not define delimiters or provide warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The runtime supports file system checks (
fileExists), console output (println), and process control (CLIExit) as documented inSKILL.md. - Sanitization: There are no instructions or examples for sanitizing, escaping, or validating external content before it is processed or output.
- [DYNAMIC_EXECUTION]: The skill describes the use of the
--bx-codeflag and the interactive REPL inSKILL.md, which allow for the execution of arbitrary BoxLang code strings at runtime. While these are standard features of a CLI runtime, their use without validation of the input strings presents a risk of executing malicious code if the inputs are sourced from untrusted or adversarial data.
Audit Metadata