contrast
Warn
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a tool execution pattern in
SKILL.mdthat usespython3 .claude/skills/ordinary-interfaces/scripts/contrast.py $ARGUMENTS. The$ARGUMENTSvariable is not enclosed in double quotes, which allows for shell command injection. A user providing an argument like; rm -rf /or using subshells could execute arbitrary commands in the environment where the agent runs. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs (color strings) which introduces a risk surface for indirect prompt injection.
- Ingestion points: The
$ARGUMENTSvariable inSKILL.mdcaptures user or context-provided data. - Boundary markers: None are present to distinguish between data and instructions.
- Capability inventory: The skill has access to the
Bashtool, allowing it to execute system commands. - Sanitization: There is no evidence of sanitization or validation of the input color values before they are passed to the shell command.
Audit Metadata