branch-create

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill uses standard version control and CLI tools (git, gh) for their intended purposes and follows best practices for user oversight.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data from GitHub issue titles.
  • Ingestion points: Issue titles retrieved via gh issue view in Step 1.
  • Boundary markers: None explicitly defined for the data read.
  • Capability inventory: Branch creation via git checkout -b in Step 3.
  • Sanitization: The instructions include a robust sanitization process in Step 2, requiring the agent to convert the title to lowercase kebab-case and remove all special characters, which effectively mitigates potential shell injection or malicious branch naming from attacker-controlled issue titles.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 06:51 PM