ai-create-pr

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard git commands (git rev-parse, git log, git diff) and shell utilities (date, basename) to inspect the repository and generate metadata for the PR note.
  • [DATA_EXPOSURE]: The skill writes output to a local Obsidian vault path ($OBSIDIAN_AI_VAULT). This is a local filesystem operation intended for organizational note-taking and does not involve exfiltration to external services.
  • [TRUSTED_SOURCE]: The skill delegates vault synchronization to another local skill (ai-commit) rather than performing direct network operations. All described actions remain within the user's controlled development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 08:31 PM
Security Audit — agent-trust-hub — ai-create-pr