ClawHub
Back to skill

Security audit

masheev-inbox-triage

Security checks for vulnerabilities and agentic risk

Overview

This skill provides user-controlled inbox triage, defaults to read-only, and requires authorization before changing internal conversation records.

Confirm the connected workspace and OAuth permissions, and consider whether your AI host may process customer messages. Review the proposed assignments, status changes, tags and notes before authorizing them. This skill does not send customer replies.

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 · SKILL.md (reported line 12)May include surrounding context.

md
use masheev-reply-with-review.
license: Apache-2.0
compatibility: >-
  Requires the Masheev MCP server (https://api.masheev.com/api/agents/mcp,
  streamable HTTP with OAuth) or the masheev CLI. Intended for MCP hosts such as
  ChatGPT, Claude, Codex, Cursor, OpenClaw, Hermes Agent and Grok.
metadata:

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
| `get_inbox_metrics`       | Volume, response and resolution figures for a period                            |

Discover the exact input fields from each tool's schema. Status and tag values
come from the workspace; do not invent new ones without asking.

## Workflow

Static analysis

No suspicious patterns detected.