The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill's instructions are focused on providing strategic methodology without interacting with the system environment or requiring special tool access.- [NO_CODE]: The skill consists entirely of descriptive Markdown and a configuration JSON. There are no scripts, binaries, or shell commands included in the package.- [PROMPT_INJECTION]: The content does not contain any phrases or patterns typical of prompt injection, such as attempts to override safety filters, extract system instructions, or act as an unrestricted agent.- [DATA_EXFILTRATION]: The skill does not perform any network requests or attempt to access sensitive local files such as credentials, SSH keys, or environment variables.- [SAFE]: Regarding indirect prompt injection (Category 8): User input enters the context via conversational prompts (ingestion point). No explicit boundary markers are present in the instructions. The skill has no capabilities (subprocess execution, file-write, or network operations) to execute commands or transmit data externally. No sanitization is performed as the output is strictly conceptual advice.

shiliuzijue