narrative-quality-auditor

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions specify a fallback to fetch reference files, such as the TALE benchmark and auditor runbook, from the author's official GitHub repository (github.com/aaron-he-zhu/aaron-marketing-skills). This represents the retrieval of vendor-owned configuration and reference materials, which is a standard procedure for this skill type.
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources, including live brand surfaces and user-provided exports. It explicitly includes a security boundary instruction for the agent to treat all fetched or pasted data as evidence to verify rather than as commands, which provides a mitigation against indirect prompt injection attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 04:16 PM
Security Audit — agent-trust-hub — narrative-quality-auditor