defuddle
Warn
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the 'defuddle' package globally from the NPM registry if it is not already present.- [COMMAND_EXECUTION]: The skill executes the 'defuddle' CLI using user-provided URLs as arguments. This creates a potential command injection surface if the URL is not properly sanitized before being passed to the shell environment.- [PROMPT_INJECTION]: The skill processes untrusted content from external web pages, creating a risk for indirect prompt injection.
- Ingestion points: Web content is fetched from user-provided URLs using the 'defuddle parse' command.
- Boundary markers: The instructions do not define boundary markers or 'ignore' instructions to isolate fetched content from the agent's context.
- Capability inventory: The skill allows the execution of shell commands and provides file system write capabilities through the '-o' output flag.
- Sanitization: No sanitization, validation, or filtering of the retrieved web content is specified.
Audit Metadata