The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to bypass safety filters, override system prompts, or extract system instructions.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access, or unauthorized network operations detected. Examples use wget only for local health checks.
[Obfuscation] (SAFE): No evidence of Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The validation script uses standard libraries and PyYAML. There is no usage of dangerous patterns like piped remote execution (curl|bash).
[Privilege Escalation] (SAFE): The skill explicitly encourages security hardening by using non-root users in Docker containers. No unauthorized use of sudo or chmod was found.
[Dynamic Execution] (SAFE): The validation script uses yaml.safe_load(), which is a secure method for parsing YAML files and prevents arbitrary code execution.

java-docker