ss-tokens
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the
Bashtool to run a local Node.js script (generate-palette.mjs) for color palette generation.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (specifically command injection) because it takes user-supplied parameters and places them directly into a shell command template without instructing the agent to perform sanitization. - Ingestion points: User-provided colors, character styles, and harmony settings for the
generate coloraction (SKILL.md). - Boundary markers: There are no boundary markers or instructions to treat the user input as data rather than potential code or commands.
- Capability inventory: The skill utilizes
Bash,Read,Write, andEdittools to interact with the project filesystem and execute code. - Sanitization: The skill lacks instructions or validation steps to sanitize or escape user input before it is interpolated into the shell command
node <styleseed-root>/engine/color/generate-palette.mjs --key-color "$USER_COLOR".
Audit Metadata