Awesome Agent Skills Security Model Card
这是可索引项目报告证据页：它保留 Awesome Agent Skills Security Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
Awesome Agent Skills Security Model Card
| Field | Value |
|---|---|
| Repository | LLMSecurity/awesome-agent-skills-security |
| Category | Agent Skill Security Resource Index |
| Stars / forks snapshot | 8 / 9 |
| Language | Markdown |
| License | CC0-1.0 |
| Raw capture | raw-github/llmsecurity_awesome-agent-skills-security.md |
| Updated by | hourly public metadata update, 2026-05-29 10:08 +0800 |
1. Role in Self Evolve
awesome-agent-skills-security curates security and benchmark resources specifically for agent skill systems and tool-use workflows. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
collect benchmark and attack references -> map skill-level vulnerabilities and mitigations -> publish curated defense pathways for agent-skill engineering teams
3. Evidence Path
web-observed GitHub page showed 8 stars, 9 forks, 17 commits, CC0-1.0 license, and README sections for benchmarks, attacks, and defenses. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Agent Skill Security Resource Index: it shows how harness/runtime/benchmark layers convert agent behavior into reproducible and auditable engineering workflows.
5. Limits
The repository was not cloned in this iteration; no benchmark run, plugin install, workflow execution, or agent loop experiment was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.