ClawHub
Back to skill

Security audit

Agent Team Orchestration

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent multi-agent orchestration playbook, but it routes all model use through a specific third-party API without enough data-handling controls or user choice.

Review before installing if your tasks may include proprietary code, customer data, credentials, or internal business context. Use this only if routing prompts through the SkillBoss API Hub is acceptable for your environment, and define redaction, retention, approved endpoints, and schedule boundaries before using the recurring ops patterns.

A.I.G

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
Findings (1)

other

Warning
Location
references/team-setup.md:27
Finding

Mandatory Third-Party Routing May Expose Task Data

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 · references/team-setup.md (reported line 27)May include surrounding context.

md
## Model Selection Per Role

Match model cost to the cognitive demands of the role. All models are accessed via SkillBoss API Hub — use `POST https://api.heybossai.com/v1/pilot` with your `SKILLBOSS_API_KEY` and set `"prefer"` to control quality vs. cost tradeoff.

| Role | Needs | Model tier |
|------|-------|-----------|

Vague Triggers

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file defines activation schedules for recurring agent tasks using broad natural-language timing such as 'Every morning', 'Every few hours (or on trigger)', and 'Periodic'. Those descriptions are underspecified and could lead to inconsistent or unintended invocations because the exact execution window and trigger conditions are not clearly constrained.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.