tone-of-voice
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided brand information and competitor data from web searches. It includes clear structural boundaries via a discovery questionnaire and output template, reducing the risk of accidental instruction obedience from processed data. As a documentation-focused skill, its capability tier is low, primarily involving reading and writing local configuration files.
- [COMMAND_EXECUTION]: The skill instructs the agent to read and write specific files within the
.agents/directory (e.g.,tone-of-voice.md). This is a standard practice for persistent configuration and context management in AI agent skills and does not involve arbitrary shell command execution. - [EXTERNAL_DOWNLOADS]: The skill utilizes web search to research competitor websites. These search operations are targeted at public domains for research purposes and do not involve downloading or executing external code or scripts.
Audit Metadata