Skills/Claude Code plugins/huggingface-skills

huggingface-skills@1.0.35

CAUTION

Publisher claims: "Build, train, evaluate, and use open source AI models, datasets, and spaces." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher huggingface · joined 0 days agoInstalls 0Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Prompt injection attempt; Prompt injection attempt. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

HIGH
Pipe-to-shell patternskills/hf-cli/SKILL.md:6 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Prompt injection attemptskills/hf-cloud-sagemaker-production-defaults/SKILL.md:157 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptskills/hf-cloud-sagemaker-production-defaults/SKILL.md:164 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsskills/hf-cloud-aws-context-discovery/SKILL.md:3 · Persistence: instructs the agent to auto-load this skill in future sessionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Auto-update or dynamic fetch configurationskills/hf-cli/SKILL.md:188 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedskills/hf-cloud-python-env-setup/scripts/setup_env.py:126 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Direct script execution from GitHub raw URLskills/huggingface-llm-trainer/SKILL.md:234 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/huggingface-datasets/SKILL.md:83 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Credential pass-through configurationskills/huggingface-vision-trainer/SKILL.md:43 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsskills/huggingface-best/SKILL.md:9 · Persistence: instructs the agent to auto-load this skill in future sessionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/plugin_versions.py:151 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedskills/hf-cloud-python-env-setup/scripts/setup_env.py:113 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsskills/hf-cloud-aws-context-discovery/SKILL.md:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationskills/huggingface-community-evals/SKILL.md:143 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Python subprocess execution detectedscripts/build_skills_index.py:60 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedskills/hf-cloud-python-env-setup/scripts/setup_env.py:68 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsskills/hf-cloud-aws-context-discovery/SKILL.md:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/hf-cloud-aws-context-discovery/SKILL.md:64 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellskills/hf-cli/SKILL.md:6 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Auto-update or dynamic fetch configurationskills/huggingface-spaces/SKILL.md:172 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Reads credential paths from the home directoryskills/hf-cloud-aws-context-discovery/SKILL.md:64 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedskills/hf-cloud-python-env-setup/scripts/setup_env.py:103 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Credential pass-through configurationskills/huggingface-vision-trainer/SKILL.md:24 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
File type combined with upload actionskills/hf-cloud-sagemaker-production-defaults/SKILL.md:336 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
References a credential file in the home directoryskills/hf-cloud-aws-context-discovery/SKILL.md:64 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File type combined with upload actionskills/huggingface-lora-space-builder/SKILL.md:376 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageskills/huggingface-datasets/SKILL.md:89 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/huggingface-datasets/SKILL.md:72 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionskills/hf-cloud-sagemaker-production-defaults/SKILL.md:349 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/hf-cli/SKILL.md:172 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionskills/huggingface-lora-space-builder/SKILL.md:375 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedskills/hf-cloud-python-env-setup/scripts/setup_env.py:53 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/run_skills_help.py:27 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim huggingface: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to Claude Code plugins, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim huggingface