style-suggest
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts untrusted user input via the
--describeand--refarguments. This input is passed verbatim to a subagent to generate visual style definitions. Maliciously crafted descriptions could attempt to influence the subagent's output or bypass the formatting constraints defined in the system prompt. - [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to perform filesystem operations and search for existing styles. While these are core functional requirements, the use of shell commands to update index files (_index.md) introduces a dependency on the integrity of the generated style names and metadata.
Audit Metadata