Skills/Claude Code plugins/fiftyone

fiftyone@1.0.3

CAUTION

Publisher claims: "Build high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher voxel51 · joined 0 days agoInstalls 0Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-26 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: Reads credential paths from the home directory; HTML comment carrying imperative instructions to the agent; Rule modification 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
Reads credential paths from the home directoryskills/fiftyone-eval-plugin/SKILL.md:322 · 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
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:6 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Rule modification attemptskills/fiftyone-dataset-import/LEROBOT-IMPORT.md:225 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsskills/fiftyone-eval-plugin/SKILL.md:79 · 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
Reads credential paths from the home directoryskills/fiftyone-eval-plugin/SKILL.md:79 · 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
CRITICAL
Rule modification attemptskills/fiftyone-dataset-import/LEROBOT-IMPORT.md:229 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsREADME.md:99 · 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
Access to sensitive file pathsskills/fiftyone-eval-plugin/SKILL.md:322 · 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
npx invocation of non-well-known package.claude-plugin/marketplace.json:89 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandskills/fiftyone-troubleshoot/SKILL.md:302 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageskills/fiftyone-voodo-design/SKILL.md:16 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsskills/fiftyone-eval-plugin/SKILL.md:120 · 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
npx invocation of non-well-known packageskills/fiftyone-voodo-design/SKILL.md:3 · 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/fiftyone-develop-plugin/SKILL.md:120 · 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/fiftyone-voodo-design/SKILL.md:18 · 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/fiftyone-voodo-design/SKILL.md:17 · 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/fiftyone-voodo-design/SKILL.md:15 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim voxel51: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Reads credential paths from the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. 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.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
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 voxel51