brand-compile

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell command execution to handle token processing. It executes a JavaScript CLI at the local path '~/Development/brand-kit/dist/src/cli.js' using Node.js for validation and compilation tasks. Additionally, it runs 'pnpm typecheck' or 'npx tsc' to verify project integrity.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes external data files without explicit security boundaries.
  • Ingestion points: The skill reads data from 'brand.yaml', 'brand-profile.yaml', and 'design-tokens.json' within the project root.
  • Boundary markers: No delimiters or 'ignore' instructions are provided to prevent the agent from following commands that might be embedded in the YAML or JSON data.
  • Capability inventory: The agent can execute system commands and perform file system writes based on the instructions derived from the input files.
  • Sanitization: There is no evidence of content validation or sanitization before the data is processed by the CLI tool or the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 02:26 PM