Skills/PyPI/workflows-mcp

workflows-mcp@10.0.0

CAUTION· not started

Publisher claims: "MCP server for DAG-based workflow execution with YAML definitions and LLM collaboration" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher qtsone · publishing for 391 daysInstalls 198Last detonated 1 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
API_KEYMEMORY_DB_PASSWORDWORKFLOW_SECRET_API_KEYWORKFLOW_SECRET_DATABASE_PASSWORDWORKFLOW_SECRET_DB_PASSWORDConfiguration, not credentials: AUDIT_FAIL_CLOSED, MEMORY_DB_ADMIN_DATABASE, MEMORY_DB_HOST, MEMORY_DB_NAME, MEMORY_DB_PORT, MEMORY_DB_USER, WORKFLOWS_IO_QUEUE_ENABLED, WORKFLOWS_JOB_HISTORY_MAX, WORKFLOWS_JOB_HISTORY_TTL, WORKFLOWS_JOB_QUEUE_ENABLED, WORKFLOWS_JOB_QUEUE_WORKERS, WORKFLOWS_JOB_TIMEOUT, WORKFLOWS_LLM_CONFIG, WORKFLOWS_LOG_LEVEL, WORKFLOWS_MAX_CONCURRENT_JOBS, WORKFLOWS_MAX_RECURSION_DEPTH, WORKFLOWS_TEMPLATE_PATHS
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for API_KEY, MEMORY_DB_PASSWORD, WORKFLOW_SECRET_API_KEY, WORKFLOW_SECRET_DATABASE_PASSWORD, WORKFLOW_SECRET_DB_PASSWORD and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx workflows-mcp

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; not started: dependency install failed; the server itself was not observed) on 2026-11-21 and scored it 72/100 (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; Credential pass-through configuration. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/workflows_mcp/engine/file_outline.py:1032 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif file_ext in [".env", ".properties"]: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/workflows_mcp/engine/file_outline.py:1164 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileselif file_ext in [".ini", ".cfg", ".conf", ".env", ".properties"]:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python exec or eval of computed codesrc/workflows_mcp/engine/resolver/security_rules.py:41 · Python exec or eval of computed code"exec(",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Credential pass-through configurationsrc/workflows_mcp/engine/resolver/proxies.py:13 · Credential pass-through configuration — agent relays sensitive credentials# Secret proxyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationsrc/workflows_mcp/engine/resolver/unified_resolver.py:704 · Credential pass-through configuration — agent relays sensitive credentials# First time - use the proxyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Auto-update or dynamic fetch configurationsrc/workflows_mcp/engine/sql/query_builder.py:229 · Auto-update or dynamic fetch configuration — agent may load new code at runtime# Apply auto-updated values and serialize JSON columnsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collects environment variables by secret-like namessrc/workflows_mcp/engine/secrets/provider.py:161 · Collects environment variables by secret-like namesfor env_var_name in os.environ.keys():Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
LOW
Dynamic module loadingsrc/workflows_mcp/engine/executor_base.py:543 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/workflows_mcp/engine/job_store.py:45 · File type combined with upload action — agent may exfiltrate local data files- jobs/*.json: Full job data (inputs, result, error)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Dynamic module loadingsrc/workflows_mcp/engine/executor_base.py:541 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/workflows_mcp/engine/executors_memory.py:149 · File type combined with upload action — agent may exfiltrate local data filesfrom .sql.postgres_backend import PostgresBackendFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/workflows_mcp/engine/job_store.py:5 · File type combined with upload action — agent may exfiltrate local data files- JSON files (jobs/*.json): Full job data including large inputs/resultsFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/workflows_mcp/server.py:114 · File type combined with upload action — agent may exfiltrate local data filesfrom .engine.sql.postgres_backend import PostgresBackendFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python exec or eval of computed codesrc/workflows_mcp/engine/resolver/security_rules.py:42 · Python exec or eval of computed code"eval(",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File type combined with upload actionsrc/workflows_mcp/tools_memory.py:23 · File type combined with upload action — agent may exfiltrate local data filesfrom .engine.sql.postgres_backend import PostgresBackendFix: 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
≈59 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for workflows-mcp@10.0.0 as of 43 min ago. This is the package itself, not its dependencies.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim qtsone: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Collects environment variables by secret-like names≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  6. Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim qtsonePropose a patch to the maintainer