create-beaver-issue

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and executes shell commands using the GitHub CLI (gh) to create issues, update Project V2 metadata, and modify existing issue bodies. These commands are central to the skill's purpose and are guarded by a mandatory confirmation step.
  • [INDIRECT_PROMPT_INJECTION]: The skill consumes configuration data from external sources, which could be manipulated by third parties with access to the repository.
  • Ingestion points: Reads configuration from the Project V2 README (via gh project view) and local state from beaver-issue-defaults.md.
  • Boundary markers: Uses fenced YAML code blocks (beaver-config) to identify configuration data within the README.
  • Capability inventory: Capabilities include gh api calls for issue creation, gh project item-edit for metadata modification, and gh issue edit for content updates.
  • Sanitization: Employs a 'Preview and confirm' workflow that displays full issue details and waits for explicit user approval before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 11:22 AM