microcopy
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external localization files and user-provided text, creating an attack surface for indirect prompt injection.
- Ingestion points: Localization files matching the glob
src/locales/default/*and raw strings provided for translation or copy refinement. - Boundary markers: The instructions lack specific delimiters (e.g., XML tags or triple quotes) or negative constraints to prevent the model from following instructions embedded within the strings being processed.
- Capability inventory: The skill is intended for use in an environment where the agent can read and modify localization files.
- Sanitization: No sanitization, filtering, or validation mechanisms are defined to handle potentially malicious input strings.
Audit Metadata