The Agent Skills Directory

[SAFE]: The skill's primary purpose is to generate JSON-based documentation and guides from repository metadata and file structures. No malicious intent or instructions were found in the skill body.
[SAFE]: No network operations, such as curl, wget, or fetch, are used to communicate with external servers.
[SAFE]: The skill does not access sensitive local files such as SSH keys, AWS credentials, or environment variables.
[SAFE]: No external packages (Python or Node.js) are installed or utilized, and no remote code is downloaded or executed.
[SAFE]: No obfuscation techniques, hidden commands, or deceptive metadata were identified.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by scanning untrusted repository files, but the risk is assessed as safe due to the lack of exploitable capabilities.
Ingestion points: Reads the repository file tree and README file content.
Boundary markers: No explicit delimiters or instructions are used to ignore embedded directives in the analyzed files.
Capability inventory: The skill is limited to generating structured JSON output and does not have access to shell execution, file-writing, or network tools.
Sanitization: No specific sanitization or filtering of codebase content is mentioned.

wiki-architect