Back to skill

Security audit

Yq Find Skills

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent skill-discovery and skill-management guide with disclosed management actions and no executable payloads, but users should confirm any mount, unmount, update, or priority change.

Before installing, users should treat recommendations as advisory and only approve mount, unmount, update, or priority-change actions they explicitly intend, especially in shared team environments.

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

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest description is written as a Chinese-only operational description ('MaxClaw技能发现元技能...') and the document consistently presents the skill behavior and outputs in Chinese, with no statement that users may choose their preferred language. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless clearly documented as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions are broad enough to activate during ordinary discussion of skills, recommendations, or team optimization rather than only on explicit invocation. In a meta-skill that can recommend, mount, unmount, or reprioritize other skills, unintended activation expands the attack surface and can lead to unauthorized or confusing workflow changes if downstream safeguards are weak or inconsistently enforced.

Content

No source excerpt is available for this finding.