create-issue-commit

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and Git to perform its primary functions. These are standard tools for developer workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests uncommitted code changes to generate issues and commit messages. This creates a surface where instructions embedded in code comments or files could influence the agent's output.
  • Ingestion points: Uncommitted changes in the local repository.
  • Boundary markers: Absent; there are no instructions to ignore instructions found within the diffs.
  • Capability inventory: Executes gh issue creation and git commit operations.
  • Sanitization: Absent; the skill does not specify validation of the content gathered from the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 09:35 PM
Security Audit — agent-trust-hub — create-issue-commit