defuddle
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
defuddlepackage globally usingnpm install -g defuddle. This is a dependency on an external package from the public NPM registry. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external URLs which creates an attack surface for indirect prompt injection.
- Ingestion points: The skill retrieves and parses external web content using
defuddle parse <url>as described inSKILL.md. - Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between the tool's output and potentially malicious instructions embedded within the fetched HTML/Markdown.
- Capability inventory: The skill includes file-writing capabilities using the
-oflag (defuddle parse <url> --md -o content.md). - Sanitization: There is no mention of sanitization, filtering, or escaping of the retrieved web content before it is presented to the agent for processing.
Audit Metadata