dev-workflow-mcp-server@1.32.8
CAUTION· startup onlyPublisher claims: "MCP server to enforce development workflow discipline" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
ADMIN_PASSWORDDATABASE_URLDEVWF_MONITOR_TOKENDEVWF_REAPER_SECRETDEVWF_REAPER_SECRETSSENTRY_ACCESS_TOKENSENTRY_AUTH_TOKENZETTLY_API_TOKENZETTLY_CLI_TOKENZETTLY_TOKENConfiguration, not credentials: ADMIN_EMAIL, ADMIN_USERNAME, DEFAULT_PRD_DISPLAY_PATH, DEV_WORKFLOW_DB_PATH, DEV_WORKFLOW_DB_TYPE, DEV_WORKFLOW_SECURITY_MODE, DEV_WORKFLOW_STATE_FILE, DEVWF_ACQUIRE_SEQ_DIR, DEVWF_AGENT, DEVWF_FLEET_LOCAL_ONLY, DEVWF_LOCAL_URL, DEVWF_MACHINE, DEVWF_MANAGED_CACHE, DEVWF_MONITOR_ENV_FILE, DEVWF_MONITOR_HEARTBEAT_MS, DEVWF_MONITOR_URL, DEVWF_PROFILE_DIR, DEVWF_PUBLIC_LOCAL_FIRST, DEVWF_REAPER_DRY_RUN, DEVWF_RELEASE_REVISION, DEVWF_RELEASE_URL, DEVWF_RELEASE_VERSION, DEVWF_SENTRY_CONFIG, DEVWF_SKIP_ZETTLY, DEVWF_STATE_ROOT, DEVWF_TEST_HOME, DEVWF_ZETTLY_ALLOW_LEGACY_CONFIG, DEVWF_ZETTLY_CONFIG, DEVWF_ZETTLY_SYNC, GITHUB_REF_NAME- Where it talks to
- programinglive.com (its own)Also monitor-host.example, githubusercontent.com, opencode.ai — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names monitor-host.example, githubusercontent.com, opencode.ai as well as its own vendor. The guard injects ADMIN_PASSWORD, DATABASE_URL, DEVWF_MONITOR_TOKEN, DEVWF_REAPER_SECRET, DEVWF_REAPER_SECRETS, SENTRY_ACCESS_TOKEN, SENTRY_AUTH_TOKEN, ZETTLY_API_TOKEN, ZETTLY_CLI_TOKEN, ZETTLY_TOKEN only into requests to programinglive.com (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 1.32.0
vet-skills diff dev-workflow-mcp-server 1.32.0 1.32.8In the sandbox, this version reached for nothing 1.32.0 did not. Compared from the two recorded runs, not from source.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-18 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Direct script execution from GitHub raw URL; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 37 s · 3 scenarios · 0 deviationsStatic findings
Q() { sudo -u postgres psql -d devwf_monitor -tAc "$1"; }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.brew install rtk || curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | shFix: Pin versions and sources; vendor anything fetched at install time.const config=readZettlyConfig({...env,ZETTLY_API_BASE:profileBase,ZETTLY_API_TOKEN:creds.token});Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const DEFAULT_MONITOR = process.env.DEVWF_MONITOR_URL || 'http://100.77.138.14:3100';Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.if(token){const config=readZettlyConfig({...env,ZETTLY_API_BASE:base,ZETTLY_API_TOKEN:token});return config?{...config,source:'windows-dpapi',expectedUserId}:null;}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.sudo -u postgres psql -d "${PG_DB}" -c "GRANT ALL ON SCHEMA public TO ${PG_USER};" > /dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.brew install rtk || curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.const nextEnv = { ...env };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Run this on bw-server (it uses sudo locally). It creates:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chown -R node:node /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.sudo -u postgres psql -tAc "SELECT 1 FROM pg_database WHERE datname='${PG_DB}'" | grep -q 1 \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.brew install rtk || curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.const config=token&&readZettlyConfig({...env,ZETTLY_API_BASE:base,ZETTLY_API_TOKEN:token});Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* node scripts/session-reaper.cjs [--monitor http://100.77.138.14:3100] [--json]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.* node scripts/session-reaper.cjs [--monitor http://100.77.138.14:3100] [--json]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.const nextEnv = { ...env };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.|| sudo -u postgres createdb -O "${PG_USER}" "${PG_DB}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# (see ~/.ssh/config; the restricted dbtunnel account is enough)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const DEFAULT_MONITOR = process.env.DEVWF_MONITOR_URL || 'http://100.77.138.14:3100';Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.sudo -u postgres psql -v ON_ERROR_STOP=1 <<SQLFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.res.json=value=>json(securityOutputFilter(value));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log("\n=== output tool ===");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.res.status(422).json({error:'Knowledge input rejected; use SecretReference.',findings:error.findings || []});Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.kill "$TUNNEL_PID" 2> /dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if [ -n "${TUNNEL_PID:-}" ] && kill -0 "$TUNNEL_PID" 2> /dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- 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 programinglive: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- 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.
- HTTP URL with a raw public IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.