The Agent Skills Directory

[SAFE]: No security issues were detected in the skill instructions or configuration files.
[PROMPT_INJECTION]: The instructions focus on architectural classification and do not attempt to override safety guidelines or bypass agent constraints.
[DATA_EXFILTRATION]: There are no hardcoded credentials, sensitive file path accesses, or unauthorized network operations.
[REMOTE_CODE_EXECUTION]: The skill does not include any external dependencies, script downloads, or dynamic execution patterns.
[INDIRECT_PROMPT_INJECTION]: The skill involves reading external repository data (documentation, ADRs, and file structure) which is an ingestion surface for indirect prompt injection. However, as the skill lacks exploitable capabilities like network access or system command execution, this surface is considered low risk.
Ingestion points: Repository documentation, Architecture Decision Records (ADRs), and project file structure (SKILL.md).
Boundary markers: Absent.
Capability inventory: None. The skill provides logical instructions without defining technical tools or subprocess calls.
Sanitization: Absent.

architecture-ownership