Skills/ClawHub/agentfarm-finder

agentfarm-finder@1.0.2

CAUTION· static only

Publisher claims: "Monitors Twitter daily at 16:00 to find and filter new AI Agent, Crypto, and DeFi projects matching specific keywords, outputting raw and curated data." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher torchesfrms · publishing for 247 daysInstalls 1,285Last detonated 14 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 2026-11-20 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Agent configured for autonomous execution without human approval. 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

MEDIUM
Python subprocess execution detectedagentfarm.sh:68 · Python subprocess execution detectedresult = subprocess.run(["bird", "search", query, "-n", str(COUNT), "--json"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL shortener detectedoutput/results.json:1 · URL shortener detected — destination cannot be verified… bridged the U.S. mortgage market with onchain capital.\n\nMeet @betrmortgage ↓ https://t.co/qSYjMCnnMA", "created_at": "Thu Apr 09 14:43:55 +0000 2026", "author": "Sky", "u…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Hidden zero-width characters detectedoutput/results.json:1 · Hidden zero-width characters detected — may conceal content…and organizing legacy data💡\n📌 Legacy Data Modernization for AI Ready Data\n🧑‍💻Kim Hajung Head of DX \n\n#엔코아 #encore #AIReadyData #AIReadiness #LLM #DataGov…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandoutput/results.json:1 · Process kill command — agent can terminate processes… voice, same blah. The swarm emergences are interesting but the quickest way to kill your bot’s personality is to send it to Moltbook.", "created_at": "Fri Apr 10 04…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Agent configured for autonomous execution without human approvaloutput/results.json:1 · Agent configured for autonomous execution without human approval…. \n\n1️⃣ pip install coinjure\n2️⃣ Connect @ClaudeCode \n3️⃣ Watch the harness autonomously let agents discover, backtest, and execute strategies safely in the market.\n\n🔧 Project Page: https://t.co/2rU8w3ExDD\n🎥 Watch it in action: ht…Fix: Declare and request only the permissions the task needs.
AST02

Cost to the agent

Instructions loaded
≈176 tok
1 file · 62 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

25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
  2. Unclaimed publisher≈ +8 on the totalClaim torchesfrms: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. URL shortener detected≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim torchesfrmsPropose a patch to the maintainer