Back to skill

Security audit

Agent Master Skills Clawhub Pkg

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners found broad activation instructions that could redirect unrelated tasks, along with a configuration-directory access alert; no malicious behavior was reported, and the overall confidence is medium.

Review the skill’s activation language and the configuration-directory reference before installing. The scan covered all three reported components; it found no executable scripts, but the verdict remains suspicious because of the broad activation instructions.

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
  • 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 (3)

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · README.md (reported line 65)May include surrounding context.

md
| **Codex CLI** / Replit Agent | `.agents/skills/` | `~/.agents/skills/` |
| **Cursor** | `.cursor/skills/` | `~/.cursor/skills/` |
| **Gemini CLI** | `.gemini/skills/` | — |
| **Google Antigravity** | `.agent/skills/` | `~/.gemini/config/skills/` |
| **Hermes Agent** | `.hermes/skills/` | `${HERMES_HOME:-$HOME/.hermes}/skills/` |
| **Grok Build** | `.grok/skills/` | `~/.grok/skills/` |
| **Devin** | `.devin/skills/` | `${XDG_CONFIG_HOME:-$HOME/.config}/devin/skills/` |

The byterover description requires activation before any work, without limiting it to knowledge-management tasks.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The byterover description says agents 'MUST use this for gathering contexts before any work,' extending its activation beyond relevant knowledge-management tasks. If an agent treats this catalog description as an authoritative instruction, it can redirect unrelated workflows into unnecessary skill use; its placement in a README reduces immediate exposure, and no data theft or malicious implementation is demonstrated.

Content

No source excerpt is available for this finding.

The using-superpowers description activates on any conversation, regardless of the user's task.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The using-superpowers description triggers 'when starting any conversation' and includes a requirement to use the Skill tool, regardless of the user's actual task. If followed during catalog ingestion or skill selection, this can impose an unsolicited workflow and additional skill loading; the excerpt does not establish destructive actions, privilege escalation, or exfiltration.

Content

No source excerpt is available for this finding.