support-reply-drafter
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of customer messages, which are interpolated directly into the prompt.
- Ingestion points: The prompt template in
SKILL.mdincludes a placeholder for the customer's full message. - Boundary markers: The instructions lack explicit delimiters (like XML tags) or safety warnings to ignore instructions embedded within the customer message.
- Capability inventory: The skill does not define any
allowed-toolsor include scripts, meaning it lacks file system, network, or command execution capabilities. - Sanitization: There is no sanitization or validation performed on the external content before it is processed by the AI.
Audit Metadata