talk-tal-skills-security
Use when the user asks about Liran Tal's talk at AI Native DevCon on skills security — including questions about the lethal trifecta / toxic flows, the Snyk research finding ~30% of ~4,000 Glow skills had security issues, malicious skill examples (SkillGuard, fake Vercel deployment skill, "buy anything", invisible-character Trojan Source skills), the confused-deputy problem, acceptance fatigue, parallels to NPM supply-chain attacks, or how to think about reviewing and sandboxing AI agent skills.
71
88%
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
The canonical home for this skill is ainativedev/aidevcon-2026-ldn
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
The corpus documents multiple explicit, deliberate malicious patterns in agent "skills" — data exfiltration (hidden PR/issues, paste services), credential and credit‑card harvesting, obfuscated/invisible‑character payloads, malicious scanner backdoors, and confused‑deputy installs — indicating definite malicious intent present in the materials.
- Repository
- AINativeDev/aidevcon-2026-ldn
- Commit
1887349
- 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.