onboarding-agent
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues were detected in the skill logic. It defines a guided conversational workflow for project planning and requirement gathering.
- [NO_CODE]: The skill consists entirely of markdown documentation and configuration without any source code, scripts, or binary files, which inherently limits the technical attack surface.
- [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface because it takes user input to generate project plans that include executable commands. However, the risk is minimized by explicit guardrails requiring user confirmation before execution and forbidding direct pushes to protected branches. 1. Ingestion points: User responses to the interview questions in SKILL.md. 2. Boundary markers: No explicit delimiters are used to distinguish user input within the generated plan template. 3. Capability inventory: The skill generates plans involving git branch management and shell command execution. 4. Sanitization: The skill does not validate or sanitize user input before incorporating it into the final plan.
Audit Metadata