unslop
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: This skill consists entirely of instructional markdown and a configuration YAML file. There are no scripts, binaries, or automated tasks that could execute commands or access the file system.
- [PROMPT_INJECTION]: The instructions provide guidance on how the AI should rewrite text (e.g., 'No em dashes', 'Prefer the plain word'). These are legitimate formatting and style instructions related to the skill's primary purpose and do not attempt to bypass safety filters or extract system prompts.
- [EXTERNAL_DOWNLOADS]: The skill mentions a source repository at
github.com/cursor/pluginsfor attribution purposes in the footer. This is a reference to a well-known service and does not involve any automated downloading or execution of remote code. - [METADATA_POISONING]: The metadata in
SKILL.mdandagents/openai.yamlaccurately describes the skill's functionality as a writing aid. There is no deceptive content hidden in the fields.
Audit Metadata