world2agent-manage@0.1.3
CAUTION· install onlyPublisher claims: "Install, list, and remove World2Agent sensors on this OpenClaw machine via the openclaw-sensor-bridge supervisor (out-of-process; signals POST to /hooks/agen..." Observed in sandbox: reads credential files.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 8 of 12 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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Authorization escalation language; Privileged sudo command; Privileged sudo command. Summary: reads credential files.
Behavior trace
Honeypot run · 3 s · 3 scenariosStatic findings
`~/.openclaw/skills/world2agent-manage/scripts/`. A developer override viaFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# via npm. The agent will surface npm's stderr (sudo prompt, EACCES, etc.) soFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.re-run with `sudo npm install -g @world2agent/openclaw-sensor-bridge`,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if [ -n "$pid" ] && kill -0 "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.err=$(cat /tmp/.w2a-hooks-err 2>/dev/null); rm -f /tmp/.w2a-hooks-errFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod 600 "$path" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.rm -f /tmp/.w2a-hooks-errFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out_err "auto-install of @world2agent/openclaw-sensor-bridge failed; you may need 'sudo npm install -g @world2agent/openclaw-sensor-bridge'"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…auto-detects the first `<PLATFORM>_HOME_CHANNEL=<handle>` entry in `~/.openclaw/.env` (priority: feishu, imessage, telegram, slack, discord, signal, whatsapp, wecom…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# --notify-to is supplied. Reads ~/.openclaw/.env for the firstFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_file="$(openclaw_home)/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.kill "$pid" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.rules to it. Do not refuse with `NO_REPLY` solely because of the securityFix: 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
23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- 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. Seen: ~/.npmrc.
- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim daibor: 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.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.