draft-shells
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill follows established patterns for project planning and task decomposition without introducing malicious instructions or dangerous capabilities.
- [DATA_EXPOSURE]: The skill interacts with local specification files in
.turbo/specs/and writes generated plans to.turbo/shells/. These operations are confined to specific project-relative paths and do not involve access to sensitive system directories, environment variables, or hardcoded credentials. - [REMOTE_CODE_EXECUTION]: There are no indicators of remote code execution. The skill does not perform network requests, download external scripts, or execute shell commands from untrusted sources.
- [PROMPT_INJECTION]: The instructional language is purely procedural and focused on task decomposition. It does not contain any patterns attempting to override agent instructions, bypass safety filters, or switch to unrestricted modes.
Audit Metadata