skills/softspark/ai-toolkit/rollback/Gen Agent Trust Hub

rollback

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python script (scripts/rollback_info.py) to execute informational system commands (e.g., git rev-parse, docker compose ps, alembic heads) to gather state context.
  • [COMMAND_EXECUTION]: The main skill body (SKILL.md) provides examples of common rollback commands for various platforms (Git, Alembic, Prisma, Kubernetes, etc.) for the agent to use when executing a rollback.
  • [SAFE_PRACTICES]: The skill includes mandatory safety requirements, such as verifying backups, confirming current and target states with the user, and performing health checks after execution.
  • [SAFE_PRACTICES]: All external references (GitHub source links) point to the vendor's own official infrastructure (github.com/softspark/*), which is consistent with the skill authorship.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 01:08 PM
Security Audit — agent-trust-hub — rollback