release
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local commands including
make checkfor automated testing and variousgitcommands (branch, commit, push) to manage the release lifecycle. These operations are standard for development automation and are used within their intended context.- [PROMPT_INJECTION]: The skill processes data from local files (.claude-plugin/plugin.jsonand.claude-plugin/marketplace.json) and accepts user input to determine the version bump type. This creates a surface for indirect prompt injection where instructions embedded in those files could attempt to influence the agent. However, the skill's scope is strictly limited to version field updates and standard Git commands, which mitigates the risk of arbitrary instruction execution.
Audit Metadata