lovstudio-optimize-tauri-backend
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to execute shell commands such as
find,ripgrep(rg), andwcto analyze the project structure and code metrics. It also suggests usingcargoandpnpmto format and check code. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes local repository files (Rust, TypeScript, and configuration files) to generate optimization recommendations.
- Ingestion points: Command outputs from
ripgrepandfind(SKILL.md Step 1, 2). - Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters when reading code content.
- Capability inventory: File system read/write, local command execution (cargo, pnpm, etc.).
- Sanitization: Absent. Content is processed directly for analysis.
Audit Metadata