emitter-prep-for-pr

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill executes several shell commands, including npm, pnpm, and git. These are used to build the project, format code, and manage version control as part of its intended PR preparation functionality.
  • Automated Git Operations: The skill automates git add, git commit, and git push operations. While these involve modifications to the repository and network activity to the remote origin, the skill includes a manual confirmation step where it shows the user what will be committed before proceeding.
  • Indirect Prompt Injection Surface: The skill accepts user-provided input for changeset types and messages which are then interpolated into markdown files and commit messages.
  • Ingestion points: User input provided during the 'Create changeset' step (file: SKILL.md).
  • Boundary markers: None explicitly defined for the generated markdown content.
  • Capability inventory: File system write access (.chronus/changes/), command execution (git commit, git push).
  • Sanitization: No specific sanitization of the user-provided message is mentioned before it is written to the file or used in the commit command.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 04:25 PM