Back to skill

Security audit

SkillBoss

Security checks for vulnerabilities and agentic risk

Overview

This plugin is a coherent paid-tool gateway, but it exposes very broad remote tool execution and email-sending authority that users should review before enabling.

Install only if you are comfortable letting agents send prompts, URLs, scraped content, generated email text, and other tool inputs to SkillBoss and downstream providers. Prefer scoped sub-wallets, low per-call budgets, per-tool allowlists where OpenClaw supports them, and human review before enabling `skillboss_send_email` or the generic `skillboss_run` dispatcher.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · .claude-plugin/marketplace.json (reported line 55)May include surrounding context.

json
"env": {
    "required": ["SKILLBOSS_API_KEY"],
    "how_to_get": {
      "trial": "curl -X POST https://www.skillboss.co/api/try/anonymous-wallet -H 'Content-Type: application/json' -d '{}'",
      "signup": "https://www.skillboss.co/console"
    }
  },

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The documented behavior sends all tool calls to https://api.skillboss.co/v1/run, creating an external transmission path for agent data. While remote APIs are expected for this kind of service, the security issue is the broad off-platform transmission of potentially sensitive prompts and content without a strongly emphasized user-facing warning or explicit scoping of what data is exported.

Content

Scanner excerpt · README.md (reported line 75)May include surrounding context.

md
## How it works

Every tool call hits `POST https://api.skillboss.co/v1/run` with your API key.
SkillBoss:

1. Validates the request against your wallet balance + `max_cost_per_call_usd` limit.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README explicitly states that every tool call is sent to a remote SkillBoss API and then routed to third-party vendors, but it does not clearly warn users that prompts, scraped content, email contents, and other potentially sensitive data may leave the local/OpenClaw environment. In an agent-plugin context, this omission is security-relevant because operators may assume tools run locally or only within OpenClaw, leading to unintentional disclosure of sensitive data to external services.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises and demonstrates network-capable operations to external services but does not declare an explicit tool scope such as permissions or allowed-tools. This weakens user and platform visibility into what the skill can access, increasing the risk of unexpected outbound requests and making review and policy enforcement harder.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

Zero-signup trial (30 seconds)

Get a real $0.50 SkillBoss API key in one curl call — no email, no credit card, rate limited to 1 per IP per day:

bash
curl -X POST https://www.skillboss.co/api/try/anonymous-wallet \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exposes web search and web scraping features that may send user-provided URLs, search queries, and retrieved page content to third-party providers, but it does not clearly warn users about that data flow. This can lead to unintentional disclosure of sensitive prompts, targets, or scraped content to external services.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill includes email-sending capability via AWS SES without clearly warning that user data or generated content may be sent to external recipients and processed by AWS. This raises the risk of accidental exfiltration of sensitive information or misuse of the agent to send unreviewed outbound communications.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · openclaw.plugin.json (reported line 21)May include surrounding context.

json
},
      "baseUrl": {
        "type": "string",
        "description": "Override for the SkillBoss API base URL. Defaults to https://api.skillboss.co/v1.",
        "default": "https://api.skillboss.co/v1"
      },
      "maxCostPerCallUsd": {

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · openclaw.plugin.json (reported line 22)May include surrounding context.

json
},
      "baseUrl": {
        "type": "string",
        "description": "Override for the SkillBoss API base URL. Defaults to https://api.skillboss.co/v1.",
        "default": "https://api.skillboss.co/v1"
      },
      "maxCostPerCallUsd": {

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · src/index.ts (reported line 64)May include surrounding context.

ts
},
      "baseUrl": {
        "type": "string",
        "description": "Override for the SkillBoss API base URL. Defaults to https://api.skillboss.co/v1.",
        "default": "https://api.skillboss.co/v1"
      },
      "maxCostPerCallUsd": {

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 80)May include surrounding context.

json
"typecheck": "tsc --noEmit"
  },
  "dependencies": {
    "@sinclair/typebox": "^0.34.0"
  },
  "devDependencies": {
    "typescript": "^5.6.0"

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 83)May include surrounding context.

json
"@sinclair/typebox": "^0.34.0"
  },
  "devDependencies": {
    "typescript": "^5.6.0"
  },
  "engines": {
    "node": ">=22.16.0"

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
README.md:30

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:63