ClawHub
Back to skill

Security audit

绩效反馈话术台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple HR performance-feedback writing skill with no code, external access, or hidden behavior found.

Safe to install for drafting performance-review conversations. Users should avoid entering unnecessary personal data and should treat outputs involving demotion, pay, discipline, or labor-law issues as drafting help only, with HR or legal review before use.

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
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger keyword "员工不服" is short and context-light, and could appear in ordinary discussion about employee disagreement rather than a clear request to invoke this specific skill. The file does not provide exclusion conditions or negative examples to narrow when this phrase should or should not activate the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The example phrases "按上面的结果改成更简短的版本" and "把这些整理成一张表" are generic editing requests that overlap with everyday assistant usage and are not uniquely tied to this skill. Without explicit scoping that these only apply after the skill is already active, they create ambiguous invocation boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.