skills/hashintel/labs/skeleton/Gen Agent Trust Hub

skeleton

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to perform project initialization, run test suites, and execute build commands (e.g., 'init project', 'run all available checks', 'run and confirm green'). These operations are limited to the local environment and are standard for a software bootstrapping utility.- [INDIRECT_PROMPT_INJECTION]: The skill accepts external input through the $ARGUMENTS variable to determine the project's tech stack and description, creating a potential surface for indirect injection.
  • Ingestion points: User-provided project description and tech stack via $ARGUMENTS in SKILL.md.
  • Boundary markers: Not present; the input is interpolated directly into the instructions.
  • Capability inventory: Includes shell command execution for project setup, testing, and building.
  • Sanitization: None specified; the agent relies on the user-provided tech stack to generate and execute commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:31 AM
Security Audit — agent-trust-hub — skeleton