AgentLearn— agent skill

AI Agent 从零开始构建智能体 — 全面、系统的开源学习教程

by cosolar·Agent Skill·github.com/cosolar/AgentLearn

Is AgentLearn safe to install?

SaferSkills independently audited AgentLearn (Agent Skill) and scored it 79/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 5 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
79/100
●●●●●●●●○○
Re-scan~30s
Latest scan
ScannedJun 28, 2026 · 129d ago
Scans run0 over 90 days
Detectors55 checks · 5 categories
Findings5 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
40
14.0 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 5 flagged

Securityscore 40 · 5 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · docs/09-驾驭工程/04-权限护栏与沙箱.md×5
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptdocs/09-驾驭工程/04-权限护栏与沙箱.md· markdown
151| 3 | **Accept Edits(接受编辑)** | 文件编辑自动通过,命令仍确认 | 让 Agent 批量改代码 |
152| 4 | **Auto(ML 分类器)** | 用分类器判断"是否安全"自动放行 | 熟练后的高频操作 |
153| 5 | **Don't Ask(不再询问)** | 已确认过的同类操作不再弹窗 | 长任务、受控环境 |
154| 6 | **Bypass(跳过权限)** | 基本不做权限判断 | 一次性可信脚本 |
155| 7 | **Ultracode(完全放开)** | 无限制自主执行 | 实验/离线沙箱 |
Occurrences
5 occurrences · first at L153, also L159, L572 +2 more
Show all 5 locations
Line
File
L153
docs/09-驾驭工程/04-权限护栏与沙箱.md
L159
docs/09-驾驭工程/04-权限护栏与沙箱.md
L572
docs/09-驾驭工程/04-权限护栏与沙箱.md
L580
docs/09-驾驭工程/04-权限护栏与沙箱.md
L611
docs/09-驾驭工程/04-权限护栏与沙箱.md
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256916b0a531165cbd7…rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
✓—All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.