skills/simota/agent-skills/prose/Gen Agent Trust Hub

prose

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown-based instructions, writing guidelines, and structured templates for UX writing. No executable scripts, network operations, or sensitive file access patterns were detected across any of the files.
  • [INDIRECT_PROMPT_INJECTION]: The skill features an attack surface for indirect prompt injection as it is designed to ingest and process external content (e.g., during a 'content audit' or 'copy review').
  • Ingestion points: External text strings, UI microcopy, and existing documentation provided by users or upstream agents like Echo or Vision (specified in SKILL.md).
  • Boundary markers: None explicitly defined to delimit external content from internal instructions.
  • Capability inventory: The skill possesses no dangerous capabilities; it does not invoke shell commands, perform file system writes, or execute network requests.
  • Sanitization: No sanitization or filtering of external content is specified.
  • Given the lack of actionable tools, this represents a low-risk surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:12 PM