en-zh-bilingual-json
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Category 8: Indirect Prompt Injection (LOW): The skill processes untrusted input from English .txt articles. An attacker could embed instructions in these articles to manipulate the agent's behavior during translation or formatting.
- Ingestion points: English .txt files provided by the user.
- Boundary markers: Absent (no explicit delimiters or instructions to ignore embedded commands are provided).
- Capability inventory: Reading text files and writing JSON files.
- Sanitization: None; the skill directly processes the text content.
Audit Metadata