brand-voice
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data provided by the user, specifically writing samples and content from external URLs.
- Ingestion points: The
Intakesection asks users to paste samples or provide a URL for analysis inSKILL.md. - Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions found within the provided samples.
- Capability inventory: The skill is restricted to text analysis and generation; it does not utilize shell commands, file writing, or network exfiltration tools within its own logic.
- Sanitization: There is no requirement for the agent to sanitize or filter the input data for potential prompt injection patterns.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not contain any scripts, executables, or configurations that would trigger automatic code execution.
Audit Metadata