defuddle

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the defuddle package globally from the NPM registry. The package is authored by the skill creator.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the defuddle CLI to parse web content and manage metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the web, creating a potential surface for indirect prompt injection.
  • Ingestion points: Web content is fetched via URL and processed by defuddle parse <url> (SKILL.md).
  • Boundary markers: None provided in the instructions to separate processed content from agent instructions.
  • Capability inventory: The agent can execute shell commands and write to the filesystem using the -o flag.
  • Sanitization: No specific sanitization or filtering of the parsed web content is defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:58 PM
Security Audit — agent-trust-hub — defuddle