brand-voice
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a document generation and content analysis tool. All identified behaviors, including file access and web searching, are consistent with its stated purpose of brand voice codification. No credential exposure, malicious command execution, or data exfiltration patterns were found.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting external data from user-provided URLs/files and WebSearch results.
- Ingestion points: User-provided content samples (Option A) and web search results for competitors (Option B) mentioned in SKILL.md.
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded commands in the source material.
- Capability inventory: Tools including Read, Write, Edit, and WebSearch are available to the agent.
- Sanitization: No explicit sanitization or validation of the external content is performed before analysis.
- Note: The risk is minimal as the analysis focuses on stylistic metrics (sentence length, vocabulary) rather than interpreting the content as executable instructions.
Audit Metadata