Skills/Glama/bolt-mcp

bolt-mcp@0.2.0

VERIFIED

Publisher claims: "Enables coding agents to surgically harvest licensed upstream code, scaffold adapters behind canonical contracts, audit seams, verify live behavior, and promote or mount proven components while preserving the host architecture." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher brittainknight · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add bolt-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-11 and scored it 80/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 24 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.1sprocessdependency install exit 0
24sclaimed7 tools: bolt_init_ledger, bolt_surgical_harvest, bolt_scaffold_adapter, bolt_audit_seams, bolt_verify_slot, bolt_registry_promote, bolt_registry_search_mount
24sprocessscript backend runs setup only
24sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/templates/isolation.mjs:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn { ...env, NODE_ENV: 'test', PYTHONDONTWRITEBYTECODE: '1' };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/harvester.mjs:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (relative.split('/').some(p => ignored.has(p) || p === '.env' || p.startsWith('.env.'))) throw new Error(`Excluded source path: ${relative}`);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtest/sandboxing.test.mjs:108 · Python subprocess execution detected… sys\nimport time\nfrom pathlib import Path\ndef execute(payload):\n child = subprocess.Popen([sys.executable, '-c', 'import time; time.sleep(60)'])\n Path('descendant.pid…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtest/polyglot.test.mjs:99 · Python subprocess execution detected…ngerous() {\n eval('1'); new Function('return 1');\n return process.env;\n}\n// subprocess.Popen([])\n// os.environ\n"; const options = await setup(t, code); const result = …Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/templates/runtime.py:59 · Python subprocess execution detectedprocess = subprocess.Popen([sys.executable, '-B', str(Path(__file__).resolve()), '--bolt-worker'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/process.mjs:12 · Process kill command — agent can terminate processesconst kill = () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontest/sandboxing.test.mjs:76 · File type combined with upload action — agent may exfiltrate local data filesconst secret = path.join(outside, 'secret.txt'), output = path.join(outside, 'output.txt'); fs.writeFileSync(secret, 'private fixture');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)test/interfaces.test.mjs:29 · MCP server using network transport (SSE/HTTP) — data sent over network…dFileSync(file, 'utf8')); assert.equal(config.other, true); assert.equal(config.mcpServers.existing.command, 'example'); assert.equal(config.mcpServers['bolt-mcp'].command, process.execPath); result = aw…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actiontest/sandboxing.test.mjs:81 · File type combined with upload action — agent may exfiltrate local data filesassert.equal(fs.readFileSync(path.join(s.projectPath, 'allowed.txt'), 'utf8'), 'allowed'); assert.equal(fs.existsSync(output), false);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈36 tok
1 file · 38 in bundle
Tool list per prompt
≈1,317 tok
7 tools · 188 per tool
Handshake
763 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 131

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.