defuddle
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the 'defuddle' package globally via 'npm install -g defuddle' in SKILL.md, which introduces a third-party dependency from the NPM registry.
- [COMMAND_EXECUTION]: The skill relies on shell command execution to run the 'defuddle' CLI for fetching and parsing web content.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of external web content. 1. Ingestion points: Content is retrieved from external URLs provided to the 'defuddle parse' command (SKILL.md). 2. Boundary markers: There are no instructions or delimiters defined to help the agent distinguish between scraped data and its own instructions (SKILL.md). 3. Capability inventory: The skill environment supports shell command execution via the 'defuddle' tool (SKILL.md). 4. Sanitization: No evidence of sanitization, escaping, or filtering of the retrieved web content is provided in the instructions (SKILL.md).
Audit Metadata