The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes use of host-provided CLI tools and search capabilities to analyze project files, which is necessary for its core function of generating architecture diagrams and documentation.
[DATA_EXPOSURE]: The script scripts/profile_store.py manages local state for user preferences and brand information. It includes security measures such as setting restricted file permissions (0o600) and explicitly blocking the storage of sensitive fields like 'password', 'token', or 'secret'.
[INDIRECT_PROMPT_INJECTION]: As the skill ingests and processes external codebases, it is susceptible to indirect prompt injection if malicious instructions are embedded in the analyzed source code. The skill's workflow includes reading manifests and configurations, but it maintains a clear separation between analysis and execution.
[DYNAMIC_EXECUTION]: The skill includes Python scripts (validate_skill.py and profile_store.py) that are used for source validation and profile management. These scripts perform standard file I/O and data processing without utilizing dangerous functions like eval() on untrusted input.

lov-architecture-documentation