ClawHub
Back to skill

Security audit

Metrics Track

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent metrics-planning helper that reads project context and writes a limited metrics plan document, with no evidence of hidden execution, exfiltration, or destructive behavior.

Before installing, be aware that invoking this skill can create or overwrite `docs/metrics-plan.md`. Review the generated metrics plan before committing it, especially in repositories where broad analytics or business-decision guidance may be sensitive.

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
95% confidence
Finding

The invocation hints include broad phrases like 'set up metrics', 'track KPIs', and 'success metrics', which are common in ordinary product discussions and can cause the skill to activate when a user did not explicitly intend to run it. Because the skill reads project files and writes docs/metrics-plan.md, accidental invocation can lead to unnecessary repository modification and analytics guidance being generated in the wrong context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly writes a new file to docs/metrics-plan.md but does not tell the user up front that executing the skill will modify the repository. This creates a transparency and consent issue: if the skill is auto-invoked or used in a sensitive repo, it can make unexpected changes that may be committed, reviewed, or acted on without the user's prior awareness.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.