skills/siberius/ui-cliche/prose-en/Gen Agent Trust Hub

prose-en

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown text for prose editing and stylistic auditing. No executable code, scripts, or binary assets are included.
  • [EXTERNAL_DOWNLOADS]: The skill references a public GitHub repository (github.com/petergyang/no-ai-slop) as the source for its methodology. This is a purely informational reference for attribution and does not involve automated downloads or runtime execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-provided text drafts. However, it lacks any high-risk capabilities (such as shell command execution, file system modifications, or network requests) that could be exploited via indirect injection. The instructions explicitly direct the agent to avoid altering technical identifiers, code, or URLs, which serves as a basic safety boundary.
  • [OBFUSCATION]: The skill mentions specific Unicode characters (U+2014 em dash and U+2013 en dash) to establish typographical rules. These are literal descriptions of characters for editing purposes and do not represent any attempt to hide malicious payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 10:35 PM