translate
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted content provided by the user or read from files. 1. Ingestion points: The skill accepts text input and reads local files (e.g., README.md) for translation as described in the Core Behavior and File Translation sections. 2. Boundary markers: The instructions lack delimiters or explicit warnings for the agent to ignore instructions embedded within the source text. 3. Capability inventory: The agent has permission to read and write files on the local filesystem. 4. Sanitization: No input validation or sanitization is performed on the data before it is included in the prompt context.
Audit Metadata