ClawHub
Back to skill

Security audit

Lark CLI Dev Hub

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Lark/Feishu project knowledge workflow that writes development summaries and release evidence, with no artifact-backed signs of hidden or malicious behavior.

Install this only if you want agents to record development work into your Lark/Feishu knowledge system. Configure the Dev Hub and hook mode deliberately, review what gets written to Feishu, and keep secrets, tokens, private keys, and full environment files out of payloads and outbox items.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
- Agent memory stores collaboration preferences and workflow style.
- Lark CLI Dev Hub stores project facts, tasks, bug evidence, pitfalls, playbooks, decisions, releases, artifacts, and AI run summaries.
- Do not write secrets, access tokens, app secrets, private keys, raw credentials, or full environment files.
- Treat Base as the structured source of truth. Docs hold long-form context. Whiteboard is a visual aid with a text summary linked back to Base.

## Local Entry Points

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is very broad and covers many common development situations, which can cause the agent to invoke this skill in contexts far beyond narrowly scoped Lark/Feishu knowledge-management tasks. Over-broad routing increases the chance of unnecessary access to project context, accidental writeback to external collaboration systems, and misuse in workflows where the user did not intend external persistence.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file defines activation conditions, so SQP-1 applies. The phrase 'whose command text includes fix, bug, or release' is relatively broad and may match many ordinary commit messages, but the document does not give exclusions or tighter constraints to clarify when the gate should not trigger.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.