使用于 Comet 需要根据有界语义评审包判断是否值得保存个人记忆、候选、更新、遗忘或跳过时。
64
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./assets/skills-zh/comet-memory/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.
The agent evaluates user-supplied memory packets and user evidence text passed via runtime input, which may contain untrusted user text.
899d1fb
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.