The Agent Skills Directory

[SAFE]: The skill is a standard utility for maintaining documentation. No malicious patterns, obfuscation, or unauthorized data access behaviors were detected.
[NO_CODE]: The skill consists entirely of instructional Markdown and does not include any scripts, executables, or code files, significantly reducing its attack surface.
[COMMAND_EXECUTION]: The skill instructions require the agent to use filesystem tools to read and write Markdown files. It includes a robust safety check in the 'Config Discovery' section that mandates a full stop if the filesystem scope is set to sensitive areas such as the OS root or user home directories.
[EXTERNAL_DOWNLOADS]: The documentation references the author's GitHub repository (github.com/vanillaflava/llm-wiki-skills) for additional context and setup guidance. This resource is relevant to the skill's stated purpose and is provided by the identified vendor.
[DATA_EXFILTRATION]: No exfiltration patterns were identified. The skill does not perform network requests or attempt to access credential files or environment variables.
[PROMPT_INJECTION]: While the skill ingests content from user-created wiki pages and interpolates it into other documents (like index.md), its instructions limit its operations to structural linking and indexing, which prevents it from being used as a vector for command or instruction injection.

wiki-integrate