skills/phoenixtw/skills/rebase/Gen Agent Trust Hub

rebase

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various git commands such as fetch, rebase, and push, along with gh commands to view PR information in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill derives branch names from user input or external command outputs for use in shell commands.
  • Ingestion points: Branch names retrieved from user prompts or the gh pr view command in SKILL.md.
  • Boundary markers: None identified in the command execution steps.
  • Capability inventory: Access to the git and gh command-line tools.
  • Sanitization: The skill does not include steps to validate or sanitize external branch names before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 07:56 PM