defuddle

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the global installation of the 'defuddle' package from the npm registry.
  • [COMMAND_EXECUTION]: The skill provides various shell commands for the 'defuddle' CLI tool to parse URLs, extract specific metadata, and write markdown output to files.
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by ingesting content from external URLs provided by the user.
  • Ingestion points: External content is retrieved using the defuddle parse <url> command mentioned in SKILL.md.
  • Boundary markers: Absent; the skill instructions do not include markers to delimit external content or directives to ignore instructions contained within the fetched data.
  • Capability inventory: The skill utilizes shell command execution and file system writes.
  • Sanitization: Absent; there is no evidence of filtering, escaping, or validation being applied to the content returned by the 'defuddle' tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 09:09 AM