translating-mobile
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural language prose and UI metadata, creating a potential injection surface. 1. Ingestion points: Source text and UI mock annotations identified in the 'Inspect the Mobile Context' section of SKILL.md. 2. Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions for the ingested prose text. 3. Capability inventory: The skill has the authority to block releases and perform structural validation on resource files. 4. Sanitization: It mandates preserving technical placeholders and formatting but lacks explicit sanitization instructions for the prose content itself.
Audit Metadata