version-release

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard development tools, including git, gh (GitHub CLI), and bun, to perform repository management tasks such as branch creation, project configuration reads, and pull request submission.
  • [PROMPT_INJECTION]: The skill directs the agent to generate pull request descriptions by ingesting commit history via git log and git diff. This represents an indirect prompt injection surface where commit messages are incorporated into the agent's context. Ingestion points: Commit history and diff data entered via git log and git diff commands. Boundary markers: None identified; commit messages are interpolated into the changelog generation prompt. Capability inventory: The skill utilizes git branch management commands and the GitHub CLI to act on the generated content. Sanitization: No sanitization or validation of the ingested commit messages is performed before they are used in prompt generation. This surface is inherent to the task of automated changelog generation and is considered a safe component of the intended workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 02:14 PM