Skills/ClawHub/skillboss-2

skillboss-2@0.1.4

BLOCKED· install only

Publisher claims: "Multi-AI gateway for fullstack apps. Build/deploy websites, React apps, SaaS, ecommerce to Cloudflare Workers. DB (D1/KV/R2), Stripe payments/subscriptions/c..." Observed in sandbox: reads credential files, sends data to heyboss.ai.

Registry ClawHubPublisher yshuolu · publishing for 253 daysInstalls 881Last detonated 1 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 19 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 28/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Credential pass-through configuration; Credential pass-through configuration; Auto-update or dynamic fetch configuration. Summary: reads credential files, sends data to heyboss.ai.

Behavior trace

Honeypot run · 16 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sfilesystemread ~/.config/skillboss/credentials.json outside project
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
15snetworkCONNECT tcp://heyboss.ai:443 · not in the allow-list, refused
15snetworkCONNECT tcp://heyboss.ai:443 · not in the allow-list, refused
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sfilesystemread ~/.config/skillboss/credentials.json outside project
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sfilesystemread ~/.config/skillboss/credentials.json outside project
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
16sfilesystemread ~/.config/skillboss/credentials.json outside project
16sprocessbundled script run in the sandbox with no arguments · not named in the instructions
16sfilesystemread ~/.config/skillboss/credentials.json outside project
16sprocess8 of 19 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
16sprocessscript backend runs setup only
16sprocessscript backend runs setup only
16sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationscripts/product-manager.js:61 · Credential pass-through configuration — agent relays sensitive credentials// Parse base URL and any query params (e.g., Vercel bypass token)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationscripts/product-manager.js:183 · Credential pass-through configuration — agent relays sensitive credentials// Build URL with optional Vercel bypass token for stagingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Auto-update or dynamic fetch configurationscripts/api-hub.js:775 · Auto-update or dynamic fetch configuration — agent may load new code at runtime* Check for updates and AUTO-UPDATE if new version availableFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationscripts/api-hub.js:764 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// Auto-update check after successful command execution (skip for version command itself)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/serve-build.js:816 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Files uploaded: ${result.fileCount}`)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Credential pass-through configurationscripts/stripe-connect.js:44 · Credential pass-through configuration — agent relays sensitive credentials* Build URL with optional Vercel bypass token for stagingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
LOW
Authorization escalation languagetemplates/worker-ecommerce/README.md:256 · Authorization escalation language · informational: not an instruction file**Admin access not working?**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionscripts/api-hub.js:355 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Audio saved to: ${args.output}`)Fix: 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 actionscripts/serve-build.js:231 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\nUploading to: ${apiUrl}/upload-static`)Fix: 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 actionscripts/serve-build.js:837 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Files uploaded: ${result.fileCount}`)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/serve-build.js:453 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Skip hidden files (except .env)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Authorization escalation languageworkflows/ecommerce/README.md:258 · Authorization escalation language · informational: not an instruction file4. **Admin bypass** - use `USER_EMAIL` carefully, only for testing/admin accessFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionscripts/api-hub.js:391 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Image saved to: ${args.output}`)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/serve-build.js:454 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (entry.name.startsWith('.') && entry.name !== '.env') {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/api-hub.js:523 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Video saved to: ${args.output}`)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Credential pass-through configurationscripts/stripe-connect.js:37 · Credential pass-through configuration — agent relays sensitive credentials// Parse base URL and any query params (e.g., Vercel bypass token for staging)Fix: 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 actionscripts/api-hub.js:436 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Transformed image saved to: ${args.output}`)Fix: 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 actionscripts/api-hub.js:413 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Upscaled image saved to: ${args.output}`)Fix: 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 actionscripts/serve-build.js:657 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\nUploading to: ${apiUrl}/upload-worker`)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,264 tok
1 file · 97 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

52 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%

An override rule (credential_read_plus_egress) caps this verdict regardless of the score. The first item below has to go before anything else counts.

  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs.
  2. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  3. Unclaimed publisher≈ +8 on the totalClaim yshuolu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  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 ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim yshuoluPropose a patch to the maintainer