ln-700-project-bootstrap
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard development commands for building projects, managing containers, and performing health checks (e.g., 'npm run build', 'dotnet build', 'docker-compose up', 'curl'). These actions are necessary for the skill's primary purpose of project orchestration and verification and do not represent a security risk.
- [PROMPT_INJECTION]: The skill processes untrusted project files to detect technology stacks, which is a surface for indirect prompt injection. 1. Ingestion points: Reads configuration files and source code in Phase 0. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded content were identified. 3. Capability inventory: The skill has extensive capabilities including file system modification, package installation, and shell command execution. 4. Sanitization: It uses static detection rules for stack identification. This behavior is inherent to the skill's function and is handled through structured workflows.
Audit Metadata