packages
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
aiwgCLI utility to perform package management tasks. It defines subcommands for listing, showing info, and removing packages via shell execution. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the use of user-supplied package names in shell commands.
- Ingestion points: User input is used to define the
<package-name>parameter inSKILL.md. - Boundary markers: No delimiters or instructions are provided to the agent to treat the package name strictly as a literal string or to ignore potential escape characters.
- Capability inventory: The skill has the ability to execute shell commands (
aiwg packages info,aiwg packages remove) in the host environment. - Sanitization: There is no instruction to validate or sanitize the package name before it is passed to the shell, which could lead to argument injection.
Audit Metadata