Security audit
Security checks for vulnerabilities and agentic risk
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.
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.
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.
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.
No suspicious patterns detected.
