hst-voice

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is entirely composed of Markdown documentation.
  • The package consists of SKILL.md, references/anachronism-check.md, and references/modes.md.
  • There are no scripts, binaries, or configuration files that execute code.
  • [SAFE]: No network or system-level access is required or attempted.
  • There are no external downloads, API calls, or file system operations defined in the skill.
  • The allowed-tools field is not present, meaning it does not leverage external tool capabilities for malicious purposes.
  • [SAFE]: The content is focused on stylistic literary emulation.
  • The instructions guide the AI to adopt a specific persona for political commentary and essays, including techniques to avoid contemporary cliches.
  • While the instructions encourage the AI to include "uncomfortable beats" or "crude" elements to maintain historical accuracy for the Thompson persona, these are creative writing constraints rather than attempts to bypass safety filters or perform harmful actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:09 AM
Security Audit — agent-trust-hub — hst-voice