defuddle

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the defuddle package via the npm package manager. This is a utility provided by the skill author for parsing web content. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external web pages, creating a vulnerability surface for indirect prompt injection. \n
  • Ingestion points: Web content retrieved via defuddle parse <url> in SKILL.md. \n
  • Boundary markers: None specified in the instructions. \n
  • Capability inventory: Network access for fetching URLs and file system writing using the -o flag in SKILL.md. \n
  • Sanitization: The tool cleans HTML to markdown, which removes script tags but does not filter natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:51 PM
Security Audit — agent-trust-hub — defuddle