safelink@0.1.4
CAUTION· install onlyPublisher claims: "Secure agent-to-agent hiring and execution skill for OpenClaw MCP with escrowed settlement, x402 facilitator payments, ERC-8004 identity/reputation checks, s..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-18 and scored it 61/100 (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; Pipe-to-shell pattern; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
…ME` + `COINBASE_CDP_API_KEY_PRIVATE_KEY`) for MPC wallet signing. Full list in `.env.example` and `_meta.json`. - **`DEPLOYER_PRIVATE_KEY`**: Used **once** by `scri…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose." Install: curl -L https://foundry.paradigm.xyz | bash && foundryup"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…sten_for_hire tool is called." runtime_files: "scripts/generate-env.ts writes .env interactively on first setup. scripts/deploy-contracts.ts writes deployed contr…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.`[SafeLink] Add to your .env:\n` +Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* 2. Set BASE_RPC_URL and DEPLOYER_PRIVATE_KEY in .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.note: "Save PRIVY_WALLET_ID=" + walletId + " to your .env to reuse this wallet",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const ENV_FILE = join(__dirname, "..", ".env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- **File writes**: `scripts/deploy-contracts.ts` writes deployed contract addresses back to `.env`. `scripts/generate-env.ts` creates `.env` interactively. Neither runs automatically on MCP startup.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const ENV_FILE = join(ROOT, ".env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.#!/usr/bin/env tsxFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…*Test files**: `tests/stress/` contains literal prompt-injection strings (e.g. `Ignore all previous instructions`) as adversarial test fixtures that verify the input-gate blocks them. These ar…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."or PRIVY_APP_ID/APP_SECRET in your .env."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose./**Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.* 1. Install Foundry: curl -L https://foundry.paradigm.xyz | bash && foundryupFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out." Install: curl -L https://foundry.paradigm.xyz | bash && foundryup"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.* 1. Install Foundry: curl -L https://foundry.paradigm.xyz | bash && foundryupFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.#!/usr/bin/env tsxFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.note: "IMPORTANT: Save COINBASE_WALLET_DATA to your .env to reuse this wallet",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.import { createPublicClient, http, type TransactionRequest, type Hash } from "viem";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.console.error("闂?BASE_RPC_URL not set in .env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.ok(`.env written (${envLines.length} variables)`);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* SafeLink interactive .env setup wizard.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."闂?DEPLOYER_PRIVATE_KEY not set in .env\n" +Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(deployOutput);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."Set COINBASE_CDP_API_KEY_NAME and COINBASE_CDP_API_KEY_PRIVATE_KEY in your .env. " +Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…_test_note: "tests/stress/ files contain literal prompt-injection strings (e.g. Ignore all previous instructions) as adversarial test fixtures to verify the input-gate blocks them. These are n…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.console.log("Loaded existing .env. Press Enter to keep existing values.\n");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.import { createHash } from "crypto";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…console.log(` SafeEscrow: ${escrowAddress}`); // 闂佸啿鍘滈崑鎾绘煃閸忓浜?Update .env 闂佸啿鍘滈崑鎾绘煃閸忓浜鹃梺鍐插帨閸嬫捇鏌嶉崗澶婁壕闂佸啿鍘滈崑鎾绘煃閸忓浜鹃梺鍐插帨閸嬫捇鏌嶉崗澶婁壕闂佸啿鍘滈崑鎾绘煃閸忓浜鹃梺鍐插帨閸嬫捇鏌嶉崗澶…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env.example"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- 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.
- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim licc921: 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.