skills/kevinslin/skills/create-task/Gen Agent Trust Hub

create-task

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the GitHub CLI (gh) to interact with GitHub repositories and projects. It executes commands such as gh issue create, gh issue edit, and gh project item-add to automate task management.
  • [DATA_EXPOSURE]: The skill includes instructions to check authentication status using gh auth status and manages project metadata. This is localized to the user's environment and the targeted GitHub repository, with no evidence of sending sensitive tokens to external third-party servers.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content (titles, bodies, and tags) to generate GitHub issues.
  • Ingestion points: User-supplied task details are gathered in SKILL.md (Step 2).
  • Boundary markers: None identified in the prompt instructions to isolate untrusted data.
  • Capability inventory: Command execution via gh CLI and file writing to /tmp/create-task-body.md as described in references/github.md.
  • Sanitization: Not explicitly defined in the instructions, relying on the agent's default handling of shell arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:52 AM
Security Audit — agent-trust-hub — create-task