skills/wkentaro/skills/make-branch/Gen Agent Trust Hub

make-branch

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a variety of Git commands to manage local and remote state, including git branch, git reset --hard, git stash, and git push. These are standard operations for the stated purpose of branch management.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes Git commit logs and diffs to suggest branch names. This involves processing untrusted repository data that could theoretically contain instructions designed to influence the agent's naming choice, though the impact is limited to the branch naming convention.
  • Ingestion points: Reads output from git log and git diff (SKILL.md).
  • Boundary markers: None explicitly defined for the diff analysis.
  • Capability inventory: Limited to shell execution of Git commands.
  • Sanitization: None detected; the skill relies on the agent to interpret the diff and generate a kebab-case string.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:34 AM
Security Audit — agent-trust-hub — make-branch