Security audit

ClawFlow

Security checks for vulnerabilities and agentic risk

Overview

ClawFlow appears to be a legitimate workflow plugin, but it needs Review because flows can run shell commands, call agents and external APIs, persist sensitive state, and be configured for unattended full-exec operation.

Install only if you intend to let OpenClaw author and run automations. Keep the approval gate enabled unless the agent is isolated, inspect flows before running them, avoid unattended full-exec agents for untrusted inputs, do not expose the optional HTTP flow server without external access controls, and avoid putting long-lived secrets into flow state or persisted env values.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description uses broad phrases like creating a workflow, automation, pipeline, or flow, which overlap with many common user intents and can cause the skill to activate in situations beyond its safest intended scope. Over-broad activation increases the chance an agent will enter a high-capability workflow-authoring context that enables execution, HTTP calls, agent delegation, and environment access without sufficiently specific user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The 'When to use this' section contains ambiguous invocation conditions such as 'user wants to chain AI calls' or 'user says create a flow,' without clear guardrails for when not to invoke the skill. In this context, ambiguity is risky because the skill exposes dangerous capabilities including shell execution, external HTTP requests, delegated agents with unrestricted exec configuration, and persistent memory operations.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution, suspicious.env_credential_access, suspicious.exposed_secret_literal

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: .ateam/worktrees/clawflow-seems-to-ignore-the-agent/src/core/runner.ts:1202
Evidence: const fn = new Function("state", `"use strict"; return !!(${resolved});`);

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: .ateam/worktrees/is-this-true-one-issue/dist/core/runner.js:917
Evidence: const fn = new Function("state", `"use strict"; return !!(${resolved});`);

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: .ateam/worktrees/is-this-true-one-issue/src/core/runner.ts:1238
Evidence: const fn = new Function("state", `"use strict"; return !!(${resolved});`);

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: .internal/docs/first draft openclaw plugin/runner.ts:485
Evidence: const fn = new Function("input", "state", `"use strict"; return (${node.run});`);

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: dist/core/runner.js:810
Evidence: const fn = new Function("state", `"use strict"; return !!(${resolved});`);

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: src/core/runner.ts:1192
Evidence: const fn = new Function("state", `"use strict"; return !!(${resolved});`);

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: .ateam/worktrees/clawflow-seems-to-ignore-the-agent/src/core/custom-steps.ts:40
Evidence: /** Resolved env (merged from flow.env + process.env). Empty object if none. */

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: .ateam/worktrees/clawflow-seems-to-ignore-the-agent/src/core/runner.ts:174
Evidence: // Seed state.env: flow defaults → shell-expand $(…) → process.env overrides

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: .ateam/worktrees/is-this-true-one-issue/dist/core/custom-steps.d.ts:18
Evidence: /** Resolved env (merged from flow.env + process.env). Empty object if none. */

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: .ateam/worktrees/is-this-true-one-issue/dist/core/runner.js:111
Evidence: // Seed state.env: flow defaults → shell-expand $(…) → process.env overrides

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: .ateam/worktrees/is-this-true-one-issue/src/core/custom-steps.ts:40
Evidence: /** Resolved env (merged from flow.env + process.env). Empty object if none. */

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: .ateam/worktrees/is-this-true-one-issue/src/core/runner.ts:178
Evidence: // Seed state.env: flow defaults → shell-expand $(…) → process.env overrides

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: .internal/docs/first draft openclaw plugin/runner.ts:277
Evidence: const apiKey = this.cfg.apiKey ?? process.env.ANTHROPIC_API_KEY;

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/core/custom-steps.d.ts:18
Evidence: /** Resolved env (merged from flow.env + process.env). Empty object if none. */

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/core/runner.js:100
Evidence: // Seed state.env: flow defaults → shell-expand $(…) → process.env overrides

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: src/core/custom-steps.ts:40
Evidence: /** Resolved env (merged from flow.env + process.env). Empty object if none. */

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: src/core/runner.ts:174
Evidence: // Seed state.env: flow defaults → shell-expand $(…) → process.env overrides

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: .ateam/worktrees/clawflow-seems-to-ignore-the-agent/tests/core.test.ts:2299
Evidence: process.env.OPENROUTER_API_KEY = "[REDACTED]";

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: .ateam/worktrees/is-this-true-one-issue/tests/core.test.ts:2442
Evidence: process.env.OPENROUTER_API_KEY = "[REDACTED]";

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: tests/core.test.ts:2252
Evidence: process.env.OPENROUTER_API_KEY = "[REDACTED]";