defuddle
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
defuddleCLI to process URLs and manage markdown output files.\n- [EXTERNAL_DOWNLOADS]: The instructions suggest installing thedefuddleutility from the npm registry using the commandnpm install -g defuddle.\n- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing content from external web pages provided by the user.\n - Ingestion points: The
defuddle parse <url>command fetches content from remote web pages into the agent's context.\n - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the skill's instructions and potentially malicious instructions embedded in the fetched web content.\n
- Capability inventory: The skill relies on shell command execution via the
defuddleutility.\n - Sanitization: The instructions do not describe any sanitization or filtering of the content retrieved from external URLs.
Audit Metadata