prompt-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown files (
SKILL.mdand thereferences/directory) that provide educational content and templates for prompt optimization. It does not include any scripts, executable binaries, or system-level tool invocations. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted user input (vague prompts) and transforming them into structured output. Although it lacks explicit boundary markers for user input, the skill has no associated capabilities—such as file writes, network requests, or shell execution—that could be exploited via an injection attack. The risk is limited to the text-transformation process itself.
- [EXTERNAL_DOWNLOADS]: The skill includes a reference link in the
metadata.originfield to a well-known service (WeChat). This link is for informational attribution only and is not fetched or executed by the agent at runtime.
Audit Metadata