Audit the installed skill library for overlapping triggers, repeated or conflicting rules, stale references, context cost, usefulness, and dependencies when reviewing built-in, extension, and third-party skills.
81%
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
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.
The skill uses WebFetch and WebSearch in online mode to verify official documentation and public links, representing low-risk ingestion of arbitrary web content.
lee-to/ai-factory
eabdfe9
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.