Skills/ClawHub/agi-farm

agi-farm@1.2.0

CAUTION· static only

Publisher claims: "Interactive setup wizard that creates a fully working multi-agent AI team on OpenClaw. One command bootstraps agents, SOUL.md personas, comms infrastructure..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher oabdelmaksoud · publishing for 263 daysInstalls 1,357Last detonated 56 min 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 2026-11-18 and scored it 60/100 (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. 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
URL with embedded credentialsdashboard-react/src/index.css:1 · URL with embedded credentials — may be phishing or credential leaking@import url('https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@300;400;500;600;700&family=Rajdhani:wght@400;500;600;700&display=swap');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedauto-dispatch.py:179 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
URL with embedded credentialsdashboard-react/dist/assets/index-DpgkYyr0.css:1 · URL with embedded credentials — may be phishing or credential leaking@import"https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@300;400;500;600;700&family=Rajdhani:wght@400;500;600;700&display=swap";*,*:befor…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedauto-dispatch.py:146 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiongenerate.py:9 · File type combined with upload action — agent may exfiltrate local data filespython3 generate.py --team-json /path/to/team.json --output /path/to/workspace/ --all-agents --sharedFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detecteddashboard.py:77 · Python subprocess execution detectedr = subprocess.run(["openclaw", "cron", "list"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiongenerate.py:10 · File type combined with upload action — agent may exfiltrate local data filespython3 generate.py --team-json /path/to/team.json --output /path/to/workspace/ --agent mainFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detecteddashboard.py:752 · Python subprocess execution detectedsubprocess.Popen(["openclaw", "cron", "run", cron_id],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/register-crons.py:74 · Python subprocess execution detectedr = subprocess.run(cmd, capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/register-crons.py:54 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/auto-dispatch.py:196 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesgenerate.py:259 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filehelp="Write shared team files (CLAUDE.md, MEMORY.md, comms/)")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiongenerate.py:11 · File type combined with upload action — agent may exfiltrate local data filespython3 generate.py --team-json /path/to/team.json --output /path/to/workspace/ --bundleFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesgenerate.py:143 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"""Write team-wide files: CLAUDE.md, MEMORY.md, comms infrastructure."""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/auto-dispatch.py:160 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/register-crons.py:117 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"message": "Knowledge synthesis: read agent outboxes, extract learnings, update MEMORY.md (≤200 lines), update SHARED_KNOWLEDGE.json, update FAILURES.md if needed.",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/register-crons.py:41 · Python subprocess execution detectedtz = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detecteddashboard.py:66 · Python subprocess execution detectedr = subprocess.run(["openclaw", "agents", "list", "--json"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈4,439 tok
1 file · 44 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

20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim oabdelmaksoud: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  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 oabdelmaksoudPropose a patch to the maintainer