The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process untrusted external data, which is an inherent surface for indirect prompt injection attacks.
Ingestion points: The search_web tool is mandated for researching current technical trends and comparisons in SKILL.md (Rule 1).
Boundary markers: The instructions do not specify any delimiters or boundary markers to help the agent distinguish between its instructions and content retrieved from the web.
Capability inventory: The skill has the capability to perform network operations via search_web and write architectural documents to the local filesystem using write_to_file.
Sanitization: There are no instructions or patterns provided to sanitize or validate the content retrieved from external sources before it is incorporated into architectural artifacts.
[NO_CODE]: The skill does not include any executable scripts, binaries, or active code files. It consists entirely of Markdown-based instructions, templates, and reference guides.

lead-architect