ClawHub
Back to skill

Security audit

product-picker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed product-evaluation workflow that saves reports locally and sends the generated Markdown report back to the user in Feishu, with no hidden code, persistence, or unrelated data access found.

Install only if you are comfortable with generated product-analysis reports being saved locally and sent as Feishu attachments. Avoid using it for confidential product, customer, or strategy data unless Feishu is an approved channel for that information.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill mandates sending the generated Markdown report to Feishu and frames this as required behavior, but it does not require any explicit user consent or warning that analysis data will be stored locally and transmitted to an external messaging platform. If the report contains sensitive business, product, or customer-related information, this creates a clear data exfiltration and privacy risk through forced off-host delivery.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This section gives concrete instructions for local file creation and mandatory attachment delivery to a Feishu conversation, including a fixed local path and a send action template. Because transmission is compulsory and no sensitivity review, consent gate, or warning is required, the skill can push potentially confidential analysis artifacts off the local system without adequate user awareness or control.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The PPT follow-on trigger accepts broad affirmative keywords such as '好的', '要', and '可以', which can easily appear in normal conversation and be misinterpreted as authorization to launch another skill. That creates a risk of unintended secondary actions, including further file processing and possible additional data sharing, without sufficiently clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown content appears to force a specific language for the generated report, and there is no visible note that the language is user-selectable or limited to a justified region-specific use case. Under the policy, fixed-language behavior without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.