Skills/Claude Code plugins/skill-creator

skill-creator@r1

CAUTION

Publisher claims: "Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher anthropics · joined 5 days agoInstalls 0Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is skill-creator@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL with embedded credentials; URL with embedded credentials; HTML comment carrying imperative instructions to the agent. 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
URL with embedded credentialsskills/skill-creator/assets/eval_review.html:9 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionskills/skill-creator/agents/grader.md:103 · 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
File type combined with upload actionskills/skill-creator/SKILL.md:205 · 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/skill-creator/eval-viewer/generate_review.py:445 · Process kill command — agent can terminate processesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedskills/skill-creator/scripts/improve_description.py:35 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
URL with embedded credentialsskills/skill-creator/eval-viewer/viewer.html:9 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionskills/skill-creator/agents/grader.md:83 · 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/skill-creator/scripts/run_eval.py:85 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandskills/skill-creator/SKILL.md:287 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedskills/skill-creator/eval-viewer/generate_review.py:291 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentskills/skill-creator/eval-viewer/viewer.html:623 · HTML comment carrying imperative instructions to the agentFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
URL with embedded credentialsskills/skill-creator/scripts/generate_report.py:41 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionskills/skill-creator/scripts/run_loop.py:313 · 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

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim anthropics: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. 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.
  6. Process kill command≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
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 anthropics