muapi-logo-creator
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input such as brand name, concept, and style, which are interpolated into a shell command. * Ingestion points: The
--brand,--concept,--style, and--colorparameters in thebash scripts/create-logo.shcall. * Boundary markers: No clear delimitation is used to prevent user input from interfering with command structure. * Capability inventory: The skill triggers local script execution viabash. * Sanitization: No evidence of input validation or escaping is present in the skill documentation. - [COMMAND_EXECUTION]: The skill performs shell command execution by invoking
bash scripts/create-logo.shwith arguments derived from user interaction.
Audit Metadata