Security audit
Security checks for vulnerabilities and agentic risk
This is a TypeScript style-guide skill with broad but disclosed activation and no evidence of hidden code, data access, persistence, or unsafe actions.
Install this if you want TypeScript style guidance to apply automatically. Be aware that it may activate on casual TypeScript mentions, so users who prefer explicit opt-in behavior may want narrower activation wording, but no hidden or high-impact behavior was found.
The skill is configured to activate whenever a user says or merely implies 'TypeScript', which is an overly broad trigger for a prompt-based skill. Broad auto-activation can cause the skill to inject its instructions into unrelated conversations, increasing the chance of prompt-scope interference, accidental invocation, or untrusted context being treated as a coding request.
The skill is configured to activate whenever the user says or implies 'TypeScript', which is a very broad trigger likely to fire during ordinary discussion rather than explicit invocation. This can cause unsolicited style-guide behavior to override user intent, create prompt-routing confusion, and increase the chance that the skill influences unrelated tasks.
The natural-language activation section states that simply mentioning TypeScript activates the skill, but it does not define boundaries for context, intent, or precedence. In a multi-skill or instruction-following environment, this ambiguity can lead to inappropriate activation, instruction conflicts, and unintended application of the skill to requests that only reference TypeScript tangentially.
No suspicious patterns detected.
