reply-in-non-native
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted incoming messages from external participants for translation. This represents a surface where an attacker could embed instructions in a message to influence the agent's output or behavior during translation.
- Ingestion points: Incoming/received messages described in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to disregard commands embedded within the text to be translated.
- Capability inventory: The skill lacks dangerous capabilities; it has no access to the file system, network, or shell commands, limiting the potential impact of an injection.
- Sanitization: No input sanitization or filtering logic is present in the instructions.
Audit Metadata