The Agent Skills Directory

[PROMPT_INJECTION]: No malicious injection patterns or safety bypass attempts were detected. The instructions labeled as CRITICAL are standard operational guidelines for the AI agent to ensure consistency and context awareness.
[DATA_EXFILTRATION]: The skill uses standard MCP tools (e.g., get_project_summary, list_module_dependencies) to gather project context. No sensitive file access (such as credentials, SSH keys, or environment files) or unauthorized network operations were found.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote code execution. It adds well-known, trusted dependencies (org.mapstruct:mapstruct) to the project's build file, which is a standard and safe practice for this type of tool.
[COMMAND_EXECUTION]: No suspicious shell command execution or privilege escalation attempts (e.g., sudo, chmod) were identified. Code writing and build file modification are handled through official agent platform tools.
[OBFUSCATION]: The skill's instructions and code snippets are clear and in plain text. No hidden content, encoded strings, or homoglyph-based obfuscation techniques were detected.
[CREDENTIALS_UNSAFE]: No hardcoded secrets or instructions to bypass secret management were found. The skill does not interact with sensitive configuration files like .env in a way that would expose secrets.

mapper-creator