pr-branch-naming

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior or high-risk patterns were detected. The skill follows security best practices by requiring explicit user confirmation before executing shell commands and performing state checks (e.g., git status, gh auth) to prevent accidental errors. All operations are confined to standard developer tools and the current repository context.\n- [PROMPT_INJECTION]: Analyzed the surface for indirect prompt injection via user input and local metadata. Given the intended use as a local development tool with human-in-the-loop confirmation, the risk is negligible.\n
  • Ingestion points: User-provided feature descriptions in $ARGUMENTS and local metadata from git status and git log.\n
  • Boundary markers: None used for interpolated values in the shell commands.\n
  • Capability inventory: Shell command execution via git checkout and gh pr create.\n
  • Sanitization: No explicit sanitization is performed, though the skill's formatting rules (lowercase, hyphen-separated) provide implicit structural constraints for branch names.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 11:05 PM
Security Audit — agent-trust-hub — pr-branch-naming