ask-kdp
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a navigational layer for Amazon KDP publishing content. It maps user queries to a routing table to identify the appropriate specialized skill or reference article.
- [PROMPT_INJECTION]: No patterns associated with prompt injection, safety bypasses, or instruction overrides were found. The persona and instructions are consistent with the skill's stated purpose.
- [DATA_EXFILTRATION]: No network operations, credential usage, or access to sensitive local files (such as SSH keys or environment variables) were detected.
- [REMOTE_CODE_EXECUTION]: The skill does not perform remote downloads or execute external scripts.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic code execution patterns are present in the instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes user questions to determine routing logic.
- Ingestion points: User questions are processed in the routing logic.
- Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: No dangerous capabilities (network, file-write, or shell execution) are present in the skill.
- Sanitization: No explicit sanitization of user input is performed before routing.
- Note: Given the lack of high-privilege capabilities, this surface is considered safe.
Audit Metadata