brand-voice-review
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes strings in project files, which are untrusted data sources.\n
- Ingestion points: UI source code (.tsx, .jsx, .vue, .svelte) and markdown files specified in the frontmatter.\n
- Boundary markers: The skill defines the target text but does not include explicit instructions to disregard embedded commands within that text.\n
- Capability inventory: No high-risk tools (file write, network, shell) are requested or utilized.\n
- Sanitization: The skill does not escape or validate ingested content.\n- [EXTERNAL_DOWNLOADS]: The skill metadata contains a URL to the author's GitHub repository for version tracking. This is an informative reference and not a functional remote code execution vector.
Audit Metadata