Skills/ClawHub/ai-collab

ai-collab@2.0.0

CAUTION· install only

Publisher claims: "Multi-agent autonomous collaboration system for two OpenClaw agents working in parallel. Use when setting up agent-to-agent communication, running a daemon a..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jeremysommerfeld8910-cpu · publishing for 264 daysInstalls 1,986Last detonated 39 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
4 of 4 bundled scripts run with no arguments, 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 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Telegram Bot API URL; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /usr/bin/grep
0.0sprocessexec /usr/bin/head
0.0sprocessexec /usr/bin/cut
0.0sprocessexited 1: (none)
0.0sprocessbundled script run in the sandbox with no arguments
0.1sfilesystemwrote ~/.openclaw/workspace/collab/chat.log
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexec /usr/bin/rm
0.1sprocessbundled script run in the sandbox with no arguments
0.1sfilesystemread ~/.openclaw/workspace/collab/chat.log outside project
0.1sprocessexec /usr/bin/wc
0.1sprocessexec /usr/bin/cat
0.1sprocessexec /usr/bin/tail
0.1sprocessexec /usr/bin/grep
0.1sprocessexec /usr/bin/sed
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexited 1: Usage: send.sh "message text"
0.1sprocess4 of 4 bundled scripts run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandscripts/daemon.sh:13 · Process kill command — agent can terminate processesif [ -f "$PIDFILE" ] && kill -0 "$(cat $PIDFILE)" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:220 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env # Shared secrets (chmod 600, never log)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Telegram Bot API URLSKILL.md:255 · Telegram Bot API URL — data will be sent to TelegramUPDATES=$(curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getUpdates?offset=$((OFFSET+1))&timeout=20")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandSKILL.md:220 · File permission modification command — agent changes file ownership/permissions.env # Shared secrets (chmod 600, never log)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsSKILL.md:231 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Never log secrets from `.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 actionSKILL.md:436 · File type combined with upload action — agent may exfiltrate local data files**Auto-approve**: Use `Bash(*)` in `~/.claude/settings.local.json`. **NEVER** use tmux send-keys cron — it sends keypresses blindly to the wrong sessions.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 pathsSKILL.md:246 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files5. Set in `~/.openclaw/.env`: `TELEGRAM_BOT_TOKEN`, `TELEGRAM_GROUP_ID`, `TELEGRAM_USER_ID`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:251 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessource ~/.openclaw/.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandSKILL.md:391 · Process kill command — agent can terminate processes[ -f "$PIDFILE" ] && kill -0 "$(cat $PIDFILE)" 2>/dev/null && pid_alive=1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Rule modification attemptexamples/jim-workflow-prompt.md:11 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 1: Plan Before You ActFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandSKILL.md:434 · Process kill command — agent can terminate processes4. Restart daemon: `kill $(cat /tmp/clawdy_daemon.pid) && sleep 1 && bash clawdy_daemon.sh`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Rule modification attemptexamples/jim-workflow-prompt.md:21 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 2: 60-Second Step TimeoutFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandSKILL.md:119 · Process kill command — agent can terminate processesif [ -f "$PIDFILE" ] && kill -0 "$(cat $PIDFILE)" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Rule modification attemptexamples/jim-workflow-prompt.md:44 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 5: Log After Every StepFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptexamples/jim-workflow-prompt.md:34 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 4: Never Ask Permission to ProceedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptexamples/jim-workflow-prompt.md:30 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 3: Never Repeat a Failed Approach TwiceFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈3,452 tok
1 file · 11 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

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jeremysommerfeld8910-cpu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. 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.
  4. Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jeremysommerfeld8910-cpuPropose a patch to the maintainer