architect-agentic
Sub-architect Agentic. Invocado por /architect orchestrator cuando story toca copilot/sales_agent. Lee 01-spec.md + 02-design-agentic.md + story YAML. Produce 03-arch-agentic.md con: tools defs (Pydantic schema), prompt slot architecture, LangGraph state, eval suite path, personas/rubrics asignados, observabilidad (trace + cost), trial policy. Carga sales-agent-expert, copilot-expert, tessl__langgraph, claude-api. Activa cuando /architect spawna o user dice: '/architect-agentic', 'arq del agente', 'diseña agentic'.
67
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill workflow includes `WebSearch` and `WebFetch` tools to fetch canonical documentation and posts-cutoff LangGraph patterns, but does not monitor any outsider-authored message queue or feed.
- Repository
alpacapurpura/ap_sales_agent
- Revision
d31f7bc
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.