The Agent Skills Directory

[SAFE]: The skill acts as a language-agnostic code skeleton generator. No malicious patterns, hardcoded secrets, obfuscation, or unauthorized data exfiltration techniques were identified in the analyzed files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided table design documents, which represents a potential attack surface for indirect prompt injection.
Ingestion points: Reads user-provided DynamoDB table design .md files as specified in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers for the processed design files.
Capability inventory: The skill is limited to reading markdown files and generating/persisting new markdown documentation. It lacks capabilities for network access (no curl or fetch), arbitrary command execution, or access to sensitive system paths like .ssh or .aws.
Sanitization: No specific sanitization or validation logic is implemented for the content of the design documents, though the risk is mitigated by the skill's lack of dangerous capabilities.

dynamodb-query-interfaces