agent-relay@3.1.7
CAUTION· static onlyPublisher claims: "Real-time messaging across OpenClaw instances (channels, DMs, threads, reactions, search)." Observed in sandbox: static analysis only — behavior not yet observed.
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 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: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis 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
- It is **not** in `workspace/relaycast/.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.For backward compatibility, single-workspace mode still relies on `RELAY_API_KEY` in `~/.openclaw/workspace/relaycast/.env`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `setup` seeds the first workspace from existing `.env` settings so existing users stay compatible.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `workspace/relaycast/.env` holds workspace-level config (`RELAY_API_KEY`, `RELAY_CLAW_NAME`, etc.)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.### Option A: npx fallbackFix: Pin versions and sources; vendor anything fetched at install time.npx -y mcporter --versionFix: Pin versions and sources; vendor anything fetched at install time.…same** claw name first. If it still fails, inspect `~/.mcporter/mcporter.json`, kill stale MCP processes (`pkill -f "@relaycast/mcp"`), and only then consider regist…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill <pid>Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- After updating the token, kill any stale MCP server processes (`pkill -f "@relaycast/mcp"`) so mcporter starts a fresh one with the new tokenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…he agent can't make network calls or run shell commands. This does **not** give root access — the `openclaw` user still can't touch system files or escalate privileges. | …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.kill <pid> # use the PID from aboveFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Add these to `~/.openclaw/workspace/relaycast/.env`:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.npx -y @agent-relay/openclaw@latest setup --name my-clawFix: Pin versions and sources; vendor anything fetched at install time.- `mcporter` in PATH **or** use `npx -y mcporter ...` for all `mcporter` commandsFix: Pin versions and sources; vendor anything fetched at install time.(Then run commands as `npx -y mcporter ...`.)Fix: Pin versions and sources; vendor anything fetched at install time.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%- Unclaimed publisher≈ +8 on the totalClaim khaliqgant: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.