lusena-new-section
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input from the $ARGUMENTS variable which is used to generate filenames and code boilerplate.\n
- Ingestion points: User input enters via the $ARGUMENTS parameter in SKILL.md.\n
- Boundary markers: Absent; there are no instructions to validate or sanitize the user-provided arguments.\n
- Capability inventory: The skill uses the Write tool to create files and the Bash tool to execute theme checks.\n
- Sanitization: Absent; user input is interpolated directly into templates and shell commands without validation.\n- [COMMAND_EXECUTION]: The skill passes user-controlled data from $ARGUMENTS directly into a shell command in the post-generation phase.\n
- Evidence: shopify theme check sections/lusena-.liquid\n
- Context: A malicious user could provide a section name containing shell metacharacters (such as semicolons or pipes) to attempt command injection, despite the tool restriction requiring the command to start with shopify theme check.
Audit Metadata