The Agent Skills Directory

[SAFE]: No security issues detected. The skill is entirely composed of text-based instructions and methodologies for business analysis.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths were found in the provided files.
[REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads, package installations, or remote code execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data, specifically Amazon buyer reviews and return reports provided by the user. While this represents a data ingestion surface, the skill lacks executable capabilities (such as shell commands or file writing) that would allow an attacker to exploit this surface.
Ingestion points: Buyer comments and return reports mentioned in SKILL.md and README_CN.md.
Boundary markers: Not present.
Capability inventory: No dangerous tools or commands detected.
Sanitization: Not specified.

amazon-return-reduction