prompt-builder
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of instructional guidelines for prompt engineering. It defines a structured approach (4 pillars: Objective, Context, Example, Constraints) to transform vague user inputs into effective AI instructions.
- [SAFE]: References to external documentation and resources, such as those from Anthropic and specific content creators, are provided for informational purposes and do not involve remote code execution or automated downloads.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied prompt strings. While this creates a theoretical surface for indirect prompt injection (where the user prompt could contain instructions targeting the builder itself), the skill lacks any dangerous capabilities (such as file system access or network operations) that could be exploited. The primary output is static text intended for human review and usage.
- [COMMAND_EXECUTION]: The skill mentions CLI flags for the Claude Code tool (e.g.,
--append-system-prompt). However, these are documented as usage examples and do not trigger any automated command execution on the host system.
Audit Metadata