The Agent Skills Directory

[Prompt Injection] (SAFE): The skill uses natural instructional language without any attempts to override system constraints or bypass safety filters.- [Data Exposure & Exfiltration] (SAFE): While the skill suggests scanning project documentation (e.g., .agents/SYSTEM/ARCHITECTURE.md) to understand context, this is a standard design pattern for context-aware agents. No external network requests or hardcoded credentials were found.- [Remote Code Execution] (SAFE): There are no scripts, package installations, or remote download patterns identified within the provided files.- [Command Execution] (SAFE): The skill does not contain any shell commands, subprocess spawning, or direct system calls.- [Obfuscation] (SAFE): No Base64 encoding, zero-width characters, or other obfuscation techniques were detected in the instructions or metadata.

workflow-automation