Back to skill

Security audit

Skillboss

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a real remote AI gateway, but it under-discloses where prompts and the API key are sent.

Review this skill before installing. Use it only if you are comfortable sending the API key, prompts, chat context, text, and media URLs to the SkillBoss/HeyBossAI remote service, and avoid including secrets or sensitive proprietary data unless that sharing is intended. Prefer a dedicated, revocable API key with spending limits, and save generated media to a non-conflicting filename or output folder.

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
scripts/run.mjs:3
Finding

Undisclosed Cross-Domain API Credential Transmission

Content
View full analysis
- Get API key at https://www.skillboss.co ``` ### Technical Analysis The script reads the `SKILLBOSS_API_KEY` environment variable and embeds its value directly in the JSON body of requests sent to `https://api.heybossai.com/v1`. This occurs both when listing models and when invoking model or task endpoints. Remote transmission of prompts and other model inputs is necessary for the declared multi-model gateway functionality. However, the Skill documentation tells users to obtain the credential from `skillboss.co` without disclosing that the key will be sent to the distinct `heybossai.com` domain. The reviewed files provide no evidence establish ...[truncated 1990 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Lp1

High
Category
MCP Least Privilege
Confidence
98% confidence
Finding

The script performs outbound network requests to api.heybossai.com but the static finding indicates this capability is not covered by declared permissions. Undeclared network access is risky because it enables external data transfer and remote interaction without clear consent or policy enforcement.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
98% confidence
Finding

The script performs outbound network requests to api.heybossai.com but the static finding indicates this capability is not covered by declared permissions. Undeclared network access is risky because it enables external data transfer and remote interaction without clear consent or policy enforcement.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill routes user prompts, text, images, and possibly other inputs to third-party AI, media, and search services, but the description does not warn users that their data leaves the local environment. This creates a real confidentiality and privacy risk because users may unknowingly send sensitive data, credentials, or proprietary content to external providers.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The hardcoded external endpoint shows that the skill is designed to transmit data to a third-party service. In the context of an agent skill that accepts arbitrary prompts, context, and media-related inputs, this external transmission meaningfully expands the data-exposure surface.

Content

Scanner excerpt · scripts/run.mjs (reported line 3)May include surrounding context.

js
#!/usr/bin/env node

const API_BASE = "https://api.heybossai.com/v1";

function usage() {
  console.error(`Usage: run.mjs [options]

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The code sends prompts, text, and chat context to an external API, but the CLI only provides general usage information and does not clearly warn users that their inputs will be transmitted off-system. This can lead to unintended disclosure of sensitive data, especially because prompts and context may contain secrets, proprietary material, or personal information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The documentation instructs users to download generated media directly to a local filename without warning that this writes untrusted remote content to disk and may overwrite existing files. While the example uses a fixed output name rather than a user-controlled path, it still normalizes saving external content locally without basic safety guidance.

Content

No source excerpt is available for this finding.