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
gitand platform-specific CLIs such asgh(GitHub) andglab(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.mdusesgit log,git rev-parse, andgit diffto 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 addandgit commit) and network operations (viagit push,gh, andglab). - Sanitization: Not explicitly implemented in the logic for interpolating branch names or diff summaries into commit messages.
Audit Metadata