The Agent Skills Directory

[SAFE]: The skill provides a professional and comprehensive methodology for technical architecture, emphasizing bounded contexts, module depth, and explicit architecture contracts.
[SAFE]: There are no indicators of malicious prompt injection, privilege escalation, or persistence mechanisms targeting the host environment.
[SAFE]: No evidence of data exfiltration or unauthorized network communication was detected; the skill operates within the context of a local workspace and coordinated toolset.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository as part of its architectural analysis workflow, which constitutes an ingestion surface.
Ingestion points: Project code, manifests, dependency files, and documentation identified in SKILL.md.
Boundary markers: The skill does not explicitly define markers to isolate ingested content from instructions, though it emphasizes evidence-based reasoning.
Capability inventory: The skill relies on local tools such as akosile for persistence and html-artifact for data visualization.
Sanitization: The instructions do not include specific sanitization or filtering steps for the ingested evidence.

solution-architect