The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a vendor-provided bash script, scripts/scan_codebase.sh, which performs file system discovery and content inspection using tools like find, grep, and cat to locate architectural patterns and hardcoded secrets.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to the ingestion of external code and documents.
Ingestion points: User-provided codebase files and design documents used during the analysis phases.
Boundary markers: None; the instructions do not implement delimiters or ignore-behavior for content within the ingested files.
Capability inventory: The skill has the ability to execute local scripts and read any file within the provided codebase path.
Sanitization: None; no validation or escaping mechanisms are applied to the analyzed content to prevent embedded instructions from influencing the agent's behavior.

architecture-reviewer