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