defuddle
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the global installation of the
defuddlepackage from the NPM registry. - [COMMAND_EXECUTION]: The skill directs the agent to execute the
defuddlecommand-line tool to process user-provided URLs. - [INDIRECT_PROMPT_INJECTION]: By fetching and processing content from external web pages, the skill creates a surface for malicious instructions to enter the agent's context.
- Ingestion points: Untrusted content from external web URLs (SKILL.md).
- Boundary markers: There are no instructions for the agent to use delimiters or ignore embedded instructions within the retrieved content.
- Capability inventory: Access to the
defuddleCLI for processing data (SKILL.md). - Sanitization: No sanitization or validation of the extracted web content is defined in the skill instructions.
Audit Metadata