ClawHub
Back to skill

Security audit

Myosin Hivemind Knowledge Retrieval

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but it handles API credentials and user queries with an unvalidated configurable endpoint that could route secrets to the wrong server.

Review before installing. Use only with a trusted HTTPS Hivemind endpoint, avoid putting confidential launch plans or secrets in search queries, and prefer runtime-injected credentials. The publisher should add endpoint allowlisting or destination binding and narrower activation guidance.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
hivemind-search.mjs:111
Finding

Unvalidated Configurable API Endpoint Can Exfiltrate Hivemind Credentials

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · hivemind-search.mjs (reported line 9)May include surrounding context.

js
import { homedir } from "node:os";

// ---------------------------------------------------------------------------
// Env resolution: process.env → .openclaw/.env → openclaw.json env object
// Only HIVEMIND_* keys are ever read from config files.
// ---------------------------------------------------------------------------

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · hivemind-search.mjs (reported line 56)May include surrounding context.

js
import { homedir } from "node:os";

// ---------------------------------------------------------------------------
// Env resolution: process.env → .openclaw/.env → openclaw.json env object
// Only HIVEMIND_* keys are ever read from config files.
// ---------------------------------------------------------------------------

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · hivemind-search.mjs (reported line 104)May include surrounding context.

js
import { homedir } from "node:os";

// ---------------------------------------------------------------------------
// Env resolution: process.env → .openclaw/.env → openclaw.json env object
// Only HIVEMIND_* keys are ever read from config files.
// ---------------------------------------------------------------------------

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · hivemind-search.mjs (reported line 125)May include surrounding context.

js
import { homedir } from "node:os";

// ---------------------------------------------------------------------------
// Env resolution: process.env → .openclaw/.env → openclaw.json env object
// Only HIVEMIND_* keys are ever read from config files.
// ---------------------------------------------------------------------------

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · hivemind-search.mjs (reported line 57)May include surrounding context.

js
const openclawDir = join(homedir(), ".openclaw");

  // 2. .openclaw/.env file — extract only the requested key
  const dotVal = loadDotEnvKey(join(openclawDir, ".env"), key);
  if (dotVal) return dotVal;

  // 3. openclaw.json → env object — extract only the requested key

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares environment-variable and network-backed behavior but does not define an explicit tool/permission scope. That weakens least-privilege controls and makes it harder for the host or reviewer to understand what capabilities the skill may exercise, increasing the chance of unintended external requests or credential use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger language is broad enough that the skill may activate during ordinary marketing discussions, causing queries to be sent externally more often than users expect. Over-invocation increases privacy and data-exposure risk, especially if user prompts contain sensitive business strategy, launch plans, or proprietary context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction to ALWAYS search before giving marketing advice creates an activation rule broader than the documented use cases and can force unnecessary external API use. This can leak user content to a third party by default and reduces the agent's ability to apply context-sensitive judgment about whether external retrieval is appropriate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explains authentication and usage but does not clearly warn that user queries may be transmitted to an external API using configured credentials. Without transparent disclosure, users may unknowingly share confidential marketing plans, token-launch details, or internal business information with a third-party service.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
hivemind-search.mjs:9