ai-collab@2.0.0
CAUTION· install onlyPublisher 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.
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 scenariosStatic findings
if [ -f "$PIDFILE" ] && kill -0 "$(cat $PIDFILE)" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell..env # Shared secrets (chmod 600, never log)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.UPDATES=$(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..env # Shared secrets (chmod 600, never log)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- Never log secrets from `.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.**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.5. 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.source ~/.openclaw/.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.[ -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.### Rule 1: Plan Before You ActFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.4. Restart daemon: `kill $(cat /tmp/clawdy_daemon.pid) && sleep 1 && bash clawdy_daemon.sh`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.### Rule 2: 60-Second Step TimeoutFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if [ -f "$PIDFILE" ] && kill -0 "$(cat $PIDFILE)" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.### Rule 5: Log After Every StepFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Rule 4: Never Ask Permission to ProceedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Rule 3: Never Repeat a Failed Approach TwiceFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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%- 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.
- 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.
- 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.
- Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.