brand-voice-enforcement
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external configuration files that could be used to deliver malicious instructions.
- Ingestion points: The skill reads .claude/brand-voice-guidelines.md and .claude/brand-voice.local.md from the user's project directory as specified in SKILL.md.
- Boundary markers: There are no clear delimiters or instructions to ignore potential commands embedded within the ingested brand guideline files.
- Capability inventory: A review of SKILL.md and the reference files indicates only text processing and generation capabilities; there are no network, file-write, or shell execution tools present in the provided files.
- Sanitization: The skill does not implement any validation or sanitization logic to filter out or ignore instructions hidden within the brand guidelines.
Audit Metadata