fizzy
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes system commands using the
fizzyCLI and usesjqto process and filter JSON output. - [PROMPT_INJECTION]: The skill processes untrusted data from the Fizzy API, which presents a surface for indirect prompt injection.
- Ingestion points: Data retrieved from
card show,card list, andcomment listcommands, as well as thewelcome_messagefield in the signup response (SKILL.md). - Boundary markers: The instructions lack delimiters or safety markers to differentiate between system instructions and data retrieved from the API.
- Capability inventory: Access to the
fizzyCLI for creating and modifying resources, and file system access for managing session tokens and HTML description files (SKILL.md). - Sanitization: There is no explicit validation or sanitization of the content retrieved from the external API before the agent processes or displays it.
Audit Metadata