continuous-learning-v2
基于本能（Instinct）的学习系统，通过钩子（hooks）观察会话，创建带有置信度评分的原子本能，并将其演化为技能（Skills）、命令（Commands）或智能体（Agents）。v2.1 版本增加了项目作用域（project-scoped）的本能，以防止跨项目污染。
63%
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/continuous-learning-v2/SKILL.mdW011: 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
Observer agent reads tool inputs/outputs and errors from locally stored `~/.claude/homunculus/projects/<project-hash>/observations.jsonl` (written by `hooks/observe.sh` from Claude Code hook stdin), so any outsider-injected free text that gets into those hook events will be ingested by the required runtime workflow.
- Repository
xu-xiang/everything-claude-code-zh
- Revision
dfbf946
- 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.