goose-migrate

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external GitHub issues which could contain malicious instructions designed to influence the agent's behavior during the migration process.
  • Ingestion points: Fetches issue titles, bodies, and labels using gh issue list in SKILL.md (Phase 1).
  • Boundary markers: The skill does not use specific delimiters or boundary markers to isolate external issue content from the agent's instructions.
  • Capability inventory: The agent can write files to the local file system (/tmp) and execute the gw todo CLI tool for task creation (Phase 5).
  • Sanitization: No explicit escaping, filtering, or sanitization is performed on the ingested content before it is interpolated into commands or file writes.
  • Mitigation: The skill incorporates a mandatory 'DRAFT' phase (Phase 4) where the user must review and approve the proposed tasks before the migration is executed.
  • [COMMAND_EXECUTION]: The skill uses shell commands to fetch data and perform batch updates.
  • Evidence: Employs gh for GitHub interactions and gw todo for Todoist task management, along with standard shell redirection (cat > /tmp/goose-migration.json) to manage temporary data. The use of single-quoted heredocs (<<'EOF') is a security best practice that prevents unintended shell expansion of the injected content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:31 AM