Use when generating or auditing a multi-role agent team package with orchestrator, workers, handoffs, Memory Ticket outputs, and runtime adapters (PM Soul, Memory Curator, Policy Gate, eval and QA are OS-resident).
76%
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
Fix and improve this skill with Tessl
tessl review fix ./skills/team-builder-packaging/SKILL.mdThe 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.
Step 2 requires the agent to actively research comparable agent repositories, academic theory, and plugin docs, which are arbitrary outsider-authored web content the agent must search for and fetch, so the attacker can publish poison but cannot force delivery.
agentlas-ai/Agentlas-OS
fdcd97a
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.