ClawHub
Back to skill

Security audit

Engineering Manager OS

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent engineering-management playbook, but it under-scopes sensitive employee profiling and performance-management guidance that could affect people's jobs.

Review this skill carefully before installing in a workplace. Use it only with approved HR processes, store any personnel notes in authorized systems, avoid collecting unnecessary personal information, and do not rely on its flight-risk or PIP guidance as a substitute for HR, legal, or company policy review.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (4)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs managers to record highly sensitive employee information such as energy level, feedback received, flight risk, performance trajectory, and private notes without any privacy, minimization, retention, or access-control guidance. In real use, this can lead to over-collection of HR-sensitive data, inappropriate storage in insecure systems, and decisions based on subjective personal profiling.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The flight-risk workflow encourages managers to infer employee intent from weak or intrusive signals like LinkedIn updates, PTO patterns, eye contact, and life events, then record and act on those inferences. This creates a meaningful risk of discriminatory profiling, privacy invasion, and unfair employment actions based on speculation rather than documented work-related evidence.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The performance-management and PIP content provides operational steps for actions that can directly affect employment status, including termination, but does not begin with a prominent HR/legal warning or require process safeguards throughout. Users may treat the template as self-sufficient and initiate disciplinary action inconsistently, unlawfully, or without required review, documentation standards, or anti-bias controls.

Scope Creep

Low
Category
Excessive Agency
Content
|-------|-------------|
| 1 - Below | Missing commitments, quality issues, needs close oversight |
| 2 - Meeting | Delivering assigned work reliably |
| 3 - Exceeding | Delivering beyond scope, finding better solutions |
| 4 - Outstanding | Multiplying team output, solving problems no one asked them to |

**Behaviors (How)**
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.