unslop
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions intended to guide the agent in editing text for clarity and naturalness. It does not define any executable code or configuration that interacts with the underlying system.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to process external text provided by users. While this creates a surface for indirect prompt injection (where the text being edited could contain instructions), the skill lacks any capabilities (such as network access, file system writes, or shell execution) to act upon malicious instructions, effectively neutralizing the risk.
- Ingestion points: Reads user-provided prose through the agent's standard context (SKILL.md).
- Boundary markers: None explicitly defined within the skill instructions.
- Capability inventory: No tool usage, network operations, or shell commands are requested or used.
- Sanitization: Not applicable as no structured data or commands are generated.
Audit Metadata