ui-lint
Warn
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple shell commands using
grep(e.g.,grep -n '#[0-9a-fA-F]\{3,8\}' [file]). These commands are used to identify hardcoded colors, pixel values, and other design violations. Since the$ARGUMENTS(representing the target files) are directly interpolated into the shell command strings, an attacker could provide a malicious filename containing characters like;,&&, or|to execute arbitrary commands on the host system. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect injection by processing untrusted data (the contents of the project files being linted) through shell pipelines.
- Ingestion points: Local project files identified via the
$ARGUMENTStarget. - Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands within the files being scanned.
- Capability inventory: The skill utilizes shell execution capabilities (
grep) across multiple check categories inSKILL.md. - Sanitization: Absent; there is no evidence of validation or escaping for the file paths or the content being processed by the shell tools.
Audit Metadata