ClawHub
Back to skill

Security audit

Source Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a source-research organizer that creates disclosed workspace notes and templates, with no evidence of hidden execution, credential access, exfiltration, or destructive behavior.

Install this if you want agents to maintain reusable source-curation records. Expect it to create or update `.source-research/` and related markdown artifacts in the current workspace; avoid enabling it in repositories where automatic research-note files are unwanted.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill explicitly instructs the agent to create and update files under `.source-research/` and to run an initialization script, but it does not declare any tool scope such as `permissions` or `allowed-tools`. That mismatch can let a host system infer or grant broader file-write capability than reviewers expect, increasing the risk of unintended workspace modification or abuse if the skill is triggered in the wrong context.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The manifest description explicitly says to use the skill when the user mentions Chinese phrases such as “信源” and “信源池,” but it does not offer a user language/locale choice or explain that the skill is intentionally region- or language-specific. This creates a natural-language policy concern because the skill appears to privilege a specific language without opt-in.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
Lines L14-L18 define suggested statuses using Chinese text while the rest of the document is in English. This creates a language-policy concern because the file effectively imposes a specific language for part of the workflow without user opt-in or justification.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The file tells the agent to create a canonical structure under `docs/source-research/` if one does not already exist. In this markdown skill description, there is no accompanying warning that the skill may modify the user's workspace or repository layout.

Static analysis

No suspicious patterns detected.