swarm@1.3.7
CAUTION· startup onlyPublisher claims: "Cut your LLM costs by 200x. Offload parallel, batch, and research work to Gemini Flash workers instead of burning your expensive primary model." Observed in sandbox: reads credential files.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-22 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Direct script execution from GitHub raw URL; Access to sensitive file paths. Summary: reads credential files.
Behavior trace
Honeypot run · 29 s · 3 scenariosStatic findings
# Usage: curl -fsSL https://raw.githubusercontent.com/clawdbot/node-scaling/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.print('\nStep 2: Enter your API key');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(` POST /parallel - Execute prompts in parallel`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(' single — merged input → 1 worker');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(' fan-out — 1 input → N workers (different perspectives)');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(` POST /research - Multi-phase research`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.# Usage: curl -fsSL https://raw.githubusercontent.com/clawdbot/node-scaling/main/install.sh | bashFix: Pin versions and sources; vendor anything fetched at install time.console.log(` Tokens: ${s.inputTokens.toLocaleString()} in / ${s.outputTokens.toLocaleString()} out`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(' reduce — N inputs → 1 synthesized output');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(' parallel — N inputs → N workers (same perspective)');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.env: { ...process.env, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Usage: curl -fsSL https://raw.githubusercontent.com/clawdbot/node-scaling/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.console.log(` POST /skeleton - Skeleton-of-Thought (outline → expand → merge)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(' --- End expected output ---\n');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(` Output: ${String(chainOutput).length} chars`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(` Duration: ${reflectDuration}ms | Output: ${reflectOutput.length} chars`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(` Duration: ${baselineDuration}ms | Output: ${baselineOutput.length} chars`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(` POST /chain/auto - Refinement pipeline (dynamic)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(`\n💾 Results saved to: ${OUTPUT_FILE}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.echo " • Add rules to AGENTS.md → Agent auto-detects parallel tasks"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Injection attempts like "ignore all previous instructions" are logged and ignoredFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.console.log(` POST /chain - Refinement pipeline (manual)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(` Output: ${sotOutput.length} chars`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log('\n🖥️ Display Output');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.throw new Error('No node-scaling configuration found. Run setup: npx node-scaling-setup');Fix: Pin versions and sources; vendor anything fetched at install time.console.log('\n3. Scoring both outputs with critic...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Users who want their agent to consider Swarm for parallelizable tasks can add guidance to their AGENTS.md file.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.console.log('\n --- Expected visual output below ---');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
17 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: ~/clawd/skills/node-scaling/.npmrc, ~/.npmrc.
- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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 chair4ce: 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.
- Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.