skill-export
Warn
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a Node.js script via a shell command:
node ${CLAUDE_PLUGIN_ROOT}/scripts/export.mjs $ARGUMENTS. This command is defined inSKILL.md. The use of the$ARGUMENTSvariable, which is populated from user input, presents a risk of command injection if the input is not sanitized to remove shell metacharacters. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data.
- Ingestion points: Untrusted data enters the context through the
<skill-name>and optional flags passed via the$ARGUMENTSvariable inSKILL.md. - Boundary markers: No delimiters or protective instructions are used to separate user data from the command context.
- Capability inventory: The skill utilizes subprocess execution of the
nodecommand to process the data. - Sanitization: There is no evidence of input validation or sanitization for the arguments being processed.
Audit Metadata