unslop
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for text editing and style improvement.
- [NO_CODE]: There are no scripts, dependencies, or executable components included in the skill. It operates solely as a writing prompt for the AI agent.
- [PROMPT_INJECTION]: The instructions do not attempt to bypass safety filters or override system-level instructions. The phrase "Must always apply" is contextually limited to the writing style guidelines provided.
- [DATA_EXFILTRATION]: No network access or sensitive file operations are requested or performed.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external text, it lacks any dangerous capabilities (such as file writing or command execution) that could be exploited via malicious input.
Audit Metadata