ship-changes

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes shell commands for version control management, specifically using git and platform-specific CLIs such as gh (GitHub) and glab (GitLab).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local repository environment, including branch names and commit history, to influence its workflow and generated commit messages.
  • Ingestion points: SKILL.md uses git log, git rev-parse, and git diff to gather context from the local filesystem and repository history.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the git logs or diffs.
  • Capability inventory: The skill can execute file writes (via git add and git commit) and network operations (via git push, gh, and glab).
  • Sanitization: Not explicitly implemented in the logic for interpolating branch names or diff summaries into commit messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 09:49 AM