toon-reference
Warn
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to run
@toon-format/toonusingnpx -y. This command downloads the package from the public npm registry without prompting the user for approval. - [REMOTE_CODE_EXECUTION]: The skill executes code from a third-party package to perform its data transformation tasks. The use of the
-yflag ensures the code runs immediately upon download. - [COMMAND_EXECUTION]: The skill provides shell command patterns for the agent to execute, including piping file contents (
cat data.json) and redirecting output (> data.toon), which involve local file system interaction. - [PROMPT_INJECTION]: The skill creates an indirect injection surface by processing untrusted user data (JSON files) through external shell commands.
- Ingestion points: Shell pipes and command line arguments in SKILL.md.
- Boundary markers: None present to distinguish data from instructions.
- Capability inventory: Subprocess execution via
npxand shell piping. - Sanitization: None detected; the skill passes raw data directly to the CLI tool.
Audit Metadata