krt-rebase-smith

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for standard Git repository maintenance. It enforces safety protocols, including the refusal to rebase protected branches (main, master, develop) and the requirement for a clean working tree before operations begin.
  • [COMMAND_EXECUTION]: The skill utilizes local Git commands to perform rebases and push updates. Destructive operations like force-pushing are protected by the use of --force-with-lease and mandatory user confirmation steps before execution.
  • [PROMPT_INJECTION]: A potential surface for indirect prompt injection exists as the skill processes Git branch names and commit logs.
  • Ingestion points: Untrusted data enters the context via git branch, git log, and git status outputs in SKILL.md.
  • Boundary markers: Not present; the skill does not explicitly delimit Git output or provide instructions to ignore embedded instructions in commit messages.
  • Capability inventory: The skill allows the execution of git switch, git rebase, and git push commands as seen in SKILL.md.
  • Sanitization: Not present; branch names and commit messages are used directly in Git commands without specific validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 08:32 PM
Security Audit — agent-trust-hub — krt-rebase-smith