llm-security
Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
76
93%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This content intentionally documents and demonstrates prompt-injection, obfuscation, exfiltration and remote-execution techniques (including explicit examples that forward messages to attacker endpoints, curl sensitive files to attacker domains, and a bootstrap-reverse script), which are high-risk backdoor/exfiltration patterns that can be abused to compromise systems.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
SKILL.md 的“当前路由未命中时，联网搜索最新漏洞利用技术”会触发在运行时获取的网页/PDF 等外部内容被浏览器/RAG 读入，从而把“他人作者的自由文本载荷”进入 LLM 上下文（间接提示注入路径）。
- Repository
- zhaoxuya520/reverse-skill
- Commit
6aa1362
- 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.