The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is entirely composed of natural language instructions guiding the agent on how to research and explain product compliance standards (e.g., FDA, CE, FCC).
[NO_CODE]: The skill does not include any scripts, executables, or package manifests. It operates purely as a prompt-based instructional set.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest user messages regarding product details and target markets to provide advice. Although this ingestion of untrusted data represents a theoretical attack surface, the skill lacks any dangerous capabilities (such as file-system writes or unauthorized network access) that could be exploited through injection, rendering the risk negligible.

amazon-product-compliance