prompt-master
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text and formatting templates. Its primary objective is to assist in the construction of LLM prompts using documented techniques. No malicious intent or dangerous patterns were identified during the analysis.
- [DATA_EXFILTRATION]: The skill does not access sensitive local data such as credentials, SSH keys, or environment variables. It performs no network operations and does not contain any exfiltration logic.
- [REMOTE_CODE_EXECUTION]: While the skill references a TypeScript file (assets/prompt-template.ts), it is utilized as a static text-based template for formatting rather than being executed as functional code. There are no mechanisms for downloading or running external scripts.
- [PROMPT_INJECTION]: The skill explicitly promotes the use of XML boundaries to separate user-provided data from system instructions, which serves as a mitigation against indirect prompt injection. No malicious override instructions or bypass attempts were found.
Audit Metadata