microcopy
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (i18n locale files and user-provided strings) for translation and copy optimization tasks.
- Ingestion points: Local files matching src/locales/default/* and user-provided text strings.
- Boundary markers: The instructions lack specific delimiters or boundary markers to isolate processed data from the agent's instructions.
- Capability inventory: The skill does not request specific tools in its frontmatter, relying on the agent's default capabilities for text processing.
- Sanitization: The skill provides instructions to preserve technical placeholders like {name} or {{count}}, but does not include security-focused sanitization or escaping rules for untrusted input.
Audit Metadata