Security audit

botlearn-twitter-intel

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Twitter/X intelligence skill made of non-executable markdown guidance, with expected public-platform analysis behavior and no hidden persistence, credential theft, or destructive actions found.

Before installing, be aware that this skill is intended to query Twitter/X and analyze public social media data. Use it only where that is appropriate, provide clear topic, time-window, language, and region scope, and ensure any Twitter/X API access complies with platform terms and privacy expectations.

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 (3)

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: Line L014 instructs operators to restrict analysis to target languages using the `lang:` operator as a default methodological step. Because this file does not explain that language selection should be based on user requirements or a documented regional scope, it risks imposing a locale constraint without explicit opt-in.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger list contains broad, common terms such as "twitter," "tweet," and especially "trending," which can match many ordinary user requests outside the intended scope. This can cause over-activation of the skill, leading the agent to invoke this capability in unrelated contexts and potentially produce unnecessary platform-specific analysis or mishandle user intent.

Missing User Warnings

Low

Confidence: 89% confidence
Finding: This markdown file instructs the skill to execute queries and collect a raw tweet corpus, which implies external network/API access and retrieval of third-party data. The document does not include any warning or disclosure to the user about this behavior, privacy implications, or reliance on external services.

Static analysis

No suspicious patterns detected.