Skills/ClawHub/model-distill-master

model-distill-master@1.0.0

CAUTION· static only

Publisher claims: "模型蒸馏大师:将大模型能力迁移到小模型的完整工作流。 支持自适应蒸馏、课程学习、能力感知、对抗训练、多维度评估。 触发词:「蒸馏模型」「把XX模型蒸馏到YY」「压缩模型」「做小模型」「教师模型分析」。 默认学生模型:gemma-3-4b-it(4B参数,适合边缘部署)。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher shixiangyu2 · publishing for 224 daysInstalls 897Last detonated 9 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Hidden zero-width characters detected. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Hidden zero-width characters detectedlanggraph_version/distill_graph.py:91 · Hidden zero-width characters detected — may conceal contentprint(f"👨‍🏫 教师模型: {teacher}")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedscripts/run_full_pipeline.py:202 · Python subprocess execution detectedsubprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/run_full_pipeline.py:257 · Python subprocess execution detectedsubprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/run_full_pipeline.py:158 · Python subprocess execution detectedsubprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionSKILL.md:558 · File type combined with upload action — agent may exfiltrate local data files输入:outputs/eval_distilled.json 和 outputs/eval_baseline.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Hidden zero-width characters detectedlanggraph_version/distill_graph.py:92 · Hidden zero-width characters detected — may conceal contentprint(f"👨‍🎓 学生模型: gemma-4-E4B-it")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedscripts/run_full_pipeline.py:220 · Python subprocess execution detectedsubprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/run_full_pipeline.py:104 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/run_full_pipeline.py:124 · Python subprocess execution detectedsubprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/run_full_pipeline.py:238 · Python subprocess execution detectedsubprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈7,569 tok
2 files · 32 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim shixiangyu2: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim shixiangyu2Propose a patch to the maintainer