elite-bootstrap
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by collecting untrusted user input to generate documentation and execute initialization commands. Evidence Chain: (1) Ingestion points: User input from the Discovery phase in SKILL.md. (2) Boundary markers: None identified; user input is directly used in plans and scaffolding logic. (3) Capability inventory: File creation (BOOTSTRAP-PLAN.md, CLAUDE.md) and command execution (framework setup, npm install) in Phase 4 of SKILL.md. (4) Sanitization: No explicit validation or sanitization of user strings is performed.
- [COMMAND_EXECUTION]: The skill uses framework-specific CLI tools to scaffold projects (e.g., create-next-app, flutter create). These are standard development operations for the skill's stated purpose and target well-known software ecosystems.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing packages and frameworks from official registries (e.g., npm, PyPI). These downloads originate from well-known technology organizations and are consistent with professional development workflows.
Audit Metadata