copywriting-tone-of-voice-creator

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites during the research phase to define tone-of-voice norms for specific brand categories.
  • Ingestion points: The skill uses WebSearch and WebFetch tools in Phase 2 to gather data from the internet about brand voice trends and reference brands.
  • Boundary markers: The instructions for the sub-agent tasked with research do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing fetched web content.
  • Capability inventory: The skill utilizes the Write tool to create TONE.md files, the Edit tool for modifications, and the Agent tool to perform sub-tasks.
  • Sanitization: There is no evidence of explicit sanitization or validation of the content retrieved from the web before it is synthesized into the final documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 07:20 AM
Security Audit — agent-trust-hub — copywriting-tone-of-voice-creator