Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed LinkedIn content-strategy guide with no code, persistence, credential use, or automatic posting behavior.
Installers should understand that the skill may prompt the agent to browse or search LinkedIn-related public content for inspiration. Review generated posts before publishing and specify your preferred language when drafting multilingual content.
The trigger description is broad enough to activate on generic professional networking or B2B content requests, which can cause the skill to be selected outside its intended scope. Over-broad activation increases prompt injection and policy-conflict risk because a marketing-oriented workflow may override more appropriate task handling in unrelated contexts.
The example shows a Chinese user request being answered in English without any indication of user preference, implying a fixed-language output policy. This can cause the agent to ignore explicit or implicit language expectations, leading to degraded usability, miscommunication, and unsafe task execution if nuance is lost in translation.
A second Chinese-input-to-English-output example reinforces a hardcoded English response pattern rather than a contextual language choice. Repetition makes the behavior more likely to be learned and applied broadly, increasing the chance of user-intent mismatch and incorrect communication in multilingual scenarios.
Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
(And what to do instead)
Slide 2:
The promise: "Generate unlimited content"
The reality: Everything looks the same
Slide 3:
No suspicious patterns detected.