anthropic-prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown files and reference templates. No security issues were detected.
- [NO_CODE]: The skill does not include any scripts, executables, or command-line tools. Its functionality is limited to providing guidance and prompt templates to the agent.
- [INDIRECT_PROMPT_INJECTION]: While the skill provides templates for processing external data (e.g., customer emails, business cards), it does not possess any dangerous capabilities such as file system writing, network requests, or code execution. The attack surface is minimal as the skill serves purely as a knowledge base for the agent's prompt generation tasks.
Audit Metadata