ClawHub
Back to skill

Security audit

x-recap

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped X recap helper that uses an authenticated browser profile to capture official account screenshots, with no evidence of hidden exfiltration, destructive behavior, or persistence beyond saved screenshot files.

Install only if you are comfortable letting the agent use an authenticated X browser profile and save local screenshots of official X pages. Review or delete saved screenshots if they may contain account identifiers, notification counts, or other private session context.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (4)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
Do not re-implement fetch logic inside cron payloads; cron should only call these scripts.

### 2) Recap from screenshots
Output rules (suggested):
- If “major update”: emit 【快报】 + <=5 bullets + impacted **software stock categories** (no tickers) + 1–2 trading-framework ideas.
- If not major: either one-liner “无重大官方更新” or stay silent (depending on user preference).

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broadly scoped around tracking, fixing, and standardizing X-related workflows, which can cause the skill to activate for a wide range of ordinary requests. Over-broad activation increases the chance the agent will enter a screenshotting/browser-automation workflow unnecessarily, exposing account context, browsing state, or captured content when the user did not explicitly request that capability.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions direct the agent to open an authenticated X profile and save screenshots, but they do not warn that screenshots may capture sensitive timeline content, DMs, account identifiers, notifications, or other private session data. In a logged-in browser context, this creates a real privacy and data-handling risk because captured images can persist on disk and be reused outside the immediate task.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The output rules require responses like "【快报】" and "无重大官方更新," which impose a specific language/locale behavior. There is no indication that the user can choose the output language or that this locale constraint is justified and documented.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.