ClawHub
Back to skill

Security audit

Achievement Unlocked

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a gamified developer-achievement tracker, but it under-explains automatic activity monitoring and team-visible profiling.

Review before installing in a work or team repository. It should clearly explain what git or review data it reads, when background tracking starts, who can see profiles and leaderboards, how long data is kept, and how users can disable or limit tracking.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
??? — "Did you just..."
  ??? — "We've all been there"
  ??? — "That's not how you spell 'Wednesday'"
  ??? — "git push --force to main? Bold."
  ??? — "3am on Christmas? Really?"
  ??? — "You fixed it by deleting the entire file"
  ??? — "11 merge conflicts resolved in one commit"
Confidence
70% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes profiling developers, tracking commits and review behavior, and displaying team-visible leaderboard information, but it does not warn users about monitoring or disclosure of potentially sensitive performance metadata. This creates privacy and workplace surveillance risk because users may be evaluated or exposed to peers without informed consent or clarity about what data is surfaced.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill states that it 'runs automatically in the background' and triggers on qualifying events, but it does not define clear trigger scope, consent, or data boundaries. In a developer tooling context, ambiguous automatic monitoring can cause unauthorized collection of work activity and surprise execution, especially if users do not understand when tracking starts or what artifacts are inspected.

Static analysis

No suspicious patterns detected.