a2ui-agent-maintenance
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override system instructions, bypass safety filters, or extract system prompts were detected. The instructions focus on repository maintenance and technical accuracy.
- [DATA_EXFILTRATION]: There are no network requests, credential harvesting, or access to sensitive environmental data (e.g., SSH keys, AWS configs). The skill works within the local documentation and specification files.
- [REMOTE_CODE_EXECUTION]: No remote scripts, package installations, or piped shell commands are present. The workflow involves reading and suggesting edits to markdown and configuration files.
- [COMMAND_EXECUTION]: The skill mentions monorepo script targets (build, lint, test) as standards to verify but does not instruct the agent to execute them with elevated privileges or on untrusted input.
- [INDIRECT_PROMPT_INJECTION]: While the skill involves reading codebase specifications and package files, it implements a safe workflow by mandating that updates are presented as suggestions for human review rather than being automatically committed.
Audit Metadata