moai-domain-humanize

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external, untrusted text for humanization across multiple languages, creating a surface for indirect prompt injection.
  • Ingestion points: Untrusted text provided by users for editing and humanization, as described in SKILL.md.
  • Boundary markers: Absent; there are no specified delimiters or instructions to ignore embedded commands within the input text.
  • Capability inventory: The skill is permitted to use Read, Write, Edit, Grep, and Glob tools according to the YAML frontmatter.
  • Sanitization: Absent; no validation or filtering of the input text is described to prevent instruction leakage.
  • [NO_CODE]: The skill is comprised entirely of instructional markdown files and contains no scripts, binaries, or external code dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 03:51 PM
Security Audit — agent-trust-hub — moai-domain-humanize