defuddle
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse and ingest content from external URLs, which creates a potential surface for indirect prompt injection where malicious instructions hidden in web pages could influence the agent's behavior. * Ingestion points: Content is fetched from remote URLs using the 'defuddle parse' command (SKILL.md). * Boundary markers: There are no instructions to use delimiters or safety wrappers to treat the output as untrusted data. * Capability inventory: The agent executes the CLI tool to fetch network data and incorporate it into the conversation context. * Sanitization: No specific sanitization or filtering of the extracted content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'defuddle' utility from the global npm registry.
- [COMMAND_EXECUTION]: The skill relies on executing the 'defuddle' command-line interface to perform its primary functions.
Audit Metadata