ClawHub
Back to skill

Security audit

developer-growth-analysis

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly says it will read recent Claude Code chat history and send a report to Slack, but that creates a real privacy review concern because it includes pasted content and lacks a mandatory approval or redaction step before external delivery.

Install only if you are comfortable letting the skill read recent Claude Code history, including pasted code or text, and send a summarized report to Slack. Before using it, ask the agent to show the report locally first, redact secrets or proprietary details, and wait for your explicit approval before any Slack message is sent.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is designed to access recent local Claude chat history and send a personalized report to Slack, but it does not require an explicit privacy notice, consent checkpoint, or review step before transmitting derived content off-device. Because chat history and pasted contents may contain secrets, internal code, credentials, or sensitive business context, this creates a meaningful risk of unintended disclosure.

Content

No source excerpt is available for this finding.

Ssd 3

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instructions explicitly direct the agent to read recent chat history, including pasted content, then analyze it for weaknesses and improvement areas. Since pasted content can contain source code, credentials, customer data, or proprietary material, this creates a direct natural-language exfiltration path from local sensitive data into a synthesized report.

Content

No source excerpt is available for this finding.

Ssd 3

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill instructs automatic delivery of the complete report to Slack DMs, which is an external channel, without a mandatory minimization or approval gate. Even if the destination is the user's own DM, Slack is still a third-party service and the report may contain sensitive summaries derived from local chat history, making external disclosure likely.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

The metadata advertises that the skill will 'automatically send' a personalized report to Slack DMs, indicating autonomous external action tied to sensitive local analysis. While not inherently malicious, this reduces user control over a high-risk operation and compounds the privacy issues elsewhere in the skill.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: developer-growth-analysis
description: Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
---

# Developer Growth Analysis

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger phrases are broad enough that ordinary requests about analyzing recent work could invoke a workflow that reads local history and sends results externally. This increases the chance of accidental activation of a privacy-sensitive skill without the user realizing it will inspect prior chats and message Slack.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.