skills/kouko/monkey-skills/defuddle/Gen Agent Trust Hub

defuddle

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends installing the "defuddle" package globally via npm.
  • [COMMAND_EXECUTION]: Utilizes the "defuddle" command-line utility to parse content from user-provided URLs.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted web content from the internet. Malicious instructions on a parsed page could attempt to influence the agent's behavior. Ingestion points: SKILL.md (defuddle parse ). Boundary markers: No delimiters or warnings are provided to segregate the fetched content. Capability inventory: Command execution via the "defuddle" tool. Sanitization: No sanitization or filtering of external content is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:05 PM
Security Audit — agent-trust-hub — defuddle