The Agent Skills Directory

[SAFE]: The skill provides instructions for a standard software engineering workflow, focusing on interface design and implementation logic. It relies on internal tool invocations for domain modeling and behavior testing.
[EXTERNAL_DOWNLOADS]: The skill references its canonical source and licensing information on GitHub. These references are for documentation and provenance purposes and do not involve the automated download or execution of remote code at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest project documentation and existing codebase context to generate architectural sketches. While this constitutes an ingestion surface for potentially untrusted data, the skill operates within the local environment and lacks capabilities for network exfiltration or unauthorized system access, mitigating the associated risk.
[METADATA_POISONING]: The skill's metadata and upstream tracking information are transparently documented, providing clear attribution to the original author and detailing local adaptations made to the skill.

pstack-architect