ClawHub
Back to skill

Security audit

knowledge-miner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed teaching helper that reads selected Git commit or visible session evidence to explain recent work, with no hidden execution, persistence, or network behavior found.

Installers should understand that this skill may read recent Git commit diffs by default when no source is specified, or visible conversation evidence when clearly requested. Avoid using it in repositories or sessions containing secrets unless you are comfortable with that content being summarized locally in the agent response.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill’s trigger description includes broad conversational phrases such as summarizing recent changes, reviewing the session, or extracting knowledge from prior context, which can overlap with many normal requests. This can cause the skill to activate when the user did not clearly request commit/session mining, leading to unnecessary repository or conversation analysis and increasing the chance of scope overreach or data exposure from nearby context.

Static analysis

No suspicious patterns detected.