ClawHub
Back to skill

Security audit

X Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small X/Twitter post reader whose network and API-key use match its stated purpose.

Install only if you are comfortable sending the requested tweet URL, tweet ID, or username to RapidAPI or public Nitter instances. If you use RapidAPI mode, treat RAPIDAPI_KEY as a normal API credential and set it only in environments where this skill should be allowed to use it.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tainted flow: 'headers' from os.getenv (line 37, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Content
}
    
    try:
        response = requests.get(url, headers=headers, params=querystring, timeout=10)
        response.raise_for_status()
        data = response.json()
Confidence
90% confidence
Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill advertises capabilities that involve environment-variable access and outbound network requests, but it does not declare any explicit tool scope or permissions. In an agent ecosystem, this weakens least-privilege controls and can lead users or orchestrators to authorize a skill without clear notice that it may read secrets from the environment and contact external services.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script sends user-supplied tweet identifiers and associated metadata to a third-party API without an explicit user-facing disclosure at runtime. In an agent-skill context, that can violate user expectations and privacy boundaries because seemingly local input triggers network transmission to an external service.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
When no API key is present, the script silently falls back to public Nitter instances and transmits the username/tweet path to those third-party services. Public scraping endpoints are less controlled and may log requests, making undisclosed fallback behavior riskier in a privacy-sensitive agent environment.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The RapidAPI mode sends the requested X/Twitter URL and associated request metadata to a third-party provider, but the skill description does not warn the user about that disclosure. This creates a privacy and transparency issue: users may unknowingly transmit sensitive targets, usage patterns, or internal investigation URLs to an external service.

Intent-Code Divergence

Low
Confidence
94% confidence
Finding
The top-level documentation says the reader uses the RapidAPI Twitter API, which suggests a single retrieval method. In reality, the code contains a separate Nitter scraping implementation and uses it whenever the RapidAPI key is absent, so the documentation does not match the actual behavior.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The script's natural-language docstrings and console messages are presented in Korean only, which imposes a specific language on users without any documented opt-in or alternative. This matches the policy concern for language/locale constraints that are not optional or justified as region-specific.

Static analysis

No suspicious patterns detected.