The Agent Skills Directory

[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were identified.
[Indirect Prompt Injection] (SAFE): The skill scripts ingest untrusted data for evaluation purposes. They lack the capabilities (network, file system, or subprocess) required to perform any malicious actions.
Ingestion points: scripts/ai_evaluator.js and scripts/ai_evaluator.py via command-line arguments.
Boundary markers: None present.
Capability inventory: Standard output logging only.
Sanitization: None present.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): No external package installations or remote script executions were detected. The scripts use standard local libraries.

ai-engineer