token-build
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to verify the design kit's presence using
lsand to run validation and contrast-checking scripts usingpython3. The referenced scripts (validate_tokens.pyandcontrast.py) are located within the project's directory structure and are used for their intended validation purposes. - [INDIRECT_PROMPT_INJECTION]: The skill processes design token files (
tokens/*.json) to generate platform artifacts, creating an attack surface for indirect prompt injection. - Ingestion points: Design token source files located at
${CLAUDE_SKILL_DIR}/../../../tokens/*.json. - Boundary markers: None identified; the instructions do not include specific delimiters or warnings to ignore embedded instructions in the token data.
- Capability inventory: The skill has capabilities for file reading, file writing (artifact generation), and command execution via
python3. - Sanitization: No explicit sanitization or filtering of the content within the design token files is described.
Audit Metadata