i18n-readiness-review
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, creating a surface where malicious instructions could be embedded in the analyzed content.
- Ingestion points: The 'Required Inputs' section in SKILL.md asks the agent to request and process external code snippets, UI screenshots, and product descriptions.
- Boundary markers: The instructions do not specify any delimiters or safety markers (such as XML tags or explicit 'ignore embedded instructions' warnings) to distinguish user-provided data from the skill's own instructions.
- Capability inventory: The skill lacks dangerous capabilities; it does not request tool access for shell execution, file system writes, or network operations, which significantly limits the potential impact of an injection.
- Sanitization: There are no instructions provided for the agent to sanitize, escape, or filter the external content before processing it for the audit.
Audit Metadata