The Agent Skills Directory

[SAFE]: No hardcoded credentials or sensitive file access was detected. The skill uses environment variables (e.g., OPENAI_API_KEY) for authentication, which is the recommended practice.
[SAFE]: External dependencies such as boto3, requests, and ollama are well-known packages from trusted sources.
[SAFE]: No signs of obfuscation, multi-layer encoding, or hidden content were found across the skill's scripts and documentation.
[SAFE]: The skill does not attempt to establish persistence, escalate privileges, or execute remote code from untrusted sources.
[SAFE]: The skill processes untrusted data (user queries and responses) for storage in Qdrant and SQLite. While this creates a standard indirect prompt injection surface for RAG-based systems, the skill does not include unsafe execution of retrieved content, and this behavior is inherent to its primary purpose.

qdrant-memory