quality-check

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill performs expected development tasks such as code linting and formatting using local scripts. Its behavior aligns with its stated purpose and common development workflows.
  • [COMMAND_EXECUTION]: The skill executes local shell scripts and npm commands. These operations are necessary for its primary function and occur within the project environment.
  • [PROMPT_INJECTION]: The skill processes output from local commands which presents an indirect prompt injection surface common to development tools.
  • Ingestion points: Command output from npm scripts in scripts/run-checks.sh is displayed to the agent.
  • Boundary markers: Output is displayed directly to the agent without specific delimiters.
  • Capability inventory: The skill uses the Bash and TodoWrite tools.
  • Sanitization: Output is not sanitized before display.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:00 AM