turn-complaints-into-polite-replies
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses a template designed to process raw customer emails via the
[PASTE EMAIL]placeholder. This introduces a surface for indirect prompt injection where an external email could contain instructions meant to influence the AI agent's behavior. - Ingestion points: The
PASTE EMAILblock inSKILL.mdis the entry point for untrusted data. - Boundary markers: The template lacks explicit delimiters (e.g., triple quotes or XML tags) or system instructions to ignore embedded commands within the user-provided text.
- Capability inventory: The skill has no capabilities to execute commands, write to the filesystem, or perform network operations. Its scope is strictly limited to text generation.
- Sanitization: No input sanitization or validation is present.
Audit Metadata