defuddle

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install an external Node.js package (defuddle) globally via the NPM registry. This package is a third-party dependency not associated with a known trusted organization.
  • [COMMAND_EXECUTION]: The skill relies on shell command execution to run the defuddle CLI. It passes user-supplied URLs directly to the parse command as arguments.
  • [PROMPT_INJECTION]: The skill ingests and cleans data from external URLs. This presents a risk of indirect prompt injection, as malicious instructions embedded in remote web content could be parsed and presented to the agent, potentially influencing its subsequent reasoning or actions.
  • Ingestion points: Content from external web pages provided via the <url> parameter (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined in the instructions for the parsed output.
  • Capability inventory: The skill is capable of shell command execution (defuddle parse).
  • Sanitization: No explicit sanitization or validation of the fetched content is described within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 01:50 PM
Security Audit — agent-trust-hub — defuddle