switch-brand
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script 'setup.py' using the 'python' command to manage brand settings. It passes the 'BRAND_SLUG' variable directly as a command-line argument.
- [INDIRECT_PROMPT_INJECTION]: The functionality to compare brand profiles involves loading external data into the agent's context, which represents an attack surface. 1. Ingestion points: Brand profile details are loaded from the filesystem (referenced in SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are specified for the comparison task. 3. Capability inventory: The skill has the ability to execute shell commands via the scripts/setup.py file. 4. Sanitization: The instructions do not specify any validation or sanitization steps for the brand profile content.
Audit Metadata