a2r-brand-voice
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is intended to process external text for reviewing and editing tasks as defined in SKILL.md. This ingestion of untrusted data without defined boundary markers or sanitization logic creates a surface for indirect prompt injection. However, the risk is limited as the skill has no dangerous capabilities (no executable code, network access, or file system operations). \n
- Ingestion points: The skill processes user-supplied text drafts for brand voice compliance checks and editing (SKILL.md). \n
- Boundary markers: No specific delimiters or 'ignore instructions' markers are defined to separate the skill instructions from the user data. \n
- Capability inventory: The skill contains no scripts, subprocesses, network calls, or file-writing operations across any of its files. \n
- Sanitization: No input validation or content filtering is specified in the prompt instructions.
Audit Metadata