fizzy
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill operates by executing the
fizzyCLI tool to perform operations on the service. This functionality is the primary intended use of the skill and is documented throughout the instructions.- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from a collaborative project management environment, which presents an attack surface for instructions embedded in user-controlled data. - Ingestion points: Untrusted data is retrieved from card titles, descriptions, and user comments via commands like
fizzy card show,fizzy comment list, andfizzy search(SKILL.md). - Boundary markers: The instructions do not define delimiters or specific 'ignore instructions' warnings when presenting retrieved content to the agent.
- Capability inventory: The agent has the ability to execute shell commands (
fizzy) that can modify account settings, manage users, and configure webhooks (SKILL.md). - Sanitization: No validation or sanitization steps are documented for handling content retrieved from the platform before processing.
Audit Metadata