defuddle
Warn
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides templates for executing shell commands, such as
defuddle parse <url> --md. If the agent interpolates user-provided URLs directly into these commands without rigorous sanitization, it could lead to command injection attacks. - [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install an external package from a public registry using
npm install -g defuddle. This introduces a dependency on third-party code that is not hosted within the skill's repository or provided by a recognized trusted vendor. - [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest and process data from external web pages, which is a significant attack surface for indirect prompt injection.
- Ingestion points: External web content retrieved from user-provided URLs (SKILL.md).
- Boundary markers: None. The instructions do not recommend using delimiters or providing specific guidance to the agent to ignore instructions found within the fetched content.
- Capability inventory: The skill has the ability to execute shell commands and write output to files (
-o content.md). - Sanitization: None. There are no instructions for filtering or escaping the fetched content before the agent processes it.
Audit Metadata