The Agent Skills Directory

[SAFE]: No malicious patterns, such as data exfiltration, command execution, or obfuscation, were identified. The skill's behavior is consistent with its stated purpose of documenting codebase architecture.
[NO_CODE]: The skill consists of markdown instructions and does not include any executable scripts or command-line operations.
[INDIRECT_PROMPT_INJECTION]: The skill ingests repository content as data, which is an untrusted source. This presents an indirect prompt injection surface where malicious instructions in the analyzed files could potentially influence the agent's summary or subsequent actions. This risk is inherent to the tool's primary purpose and is mitigated by standard agent guardrails.

custom-architecture