Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly social-media advice, but it under-discloses high-impact publishing authority and recommends large-scale scraping of third-party posts.
Review this skill carefully before installing. It is not malware, but users should treat it as a draft/advisory workflow only unless explicit approval gates are added for posting or scheduling, and scraping guidance should be narrowed to compliant sources, official exports/APIs, or user-provided examples.
The trigger description is broad enough to match many generic marketing or writing conversations, increasing the chance this skill is invoked when the user did not intend a social-media-specific workflow. Unintended invocation can cause the agent to apply the wrong capabilities or advice, which is a security-relevant routing problem even if it is not directly exploitative.
Claiming direct access to a scheduling platform that publishes to major social networks normalizes external-account actions without any consent, confirmation, or risk boundaries. In an agent context, this can lead to users or downstream systems assuming the skill may post or schedule content automatically, creating risk of unauthorized publishing, reputational damage, or misuse of connected accounts.
The skill explicitly recommends scraping 500-1000+ posts from third-party creators using automation tools such as Apify and PhantomBuster. That crosses from content advice into instructing large-scale collection of third-party platform data, which can violate platform terms, enable unauthorized data harvesting, and expose users to legal, compliance, or account-enforcement risk.
No suspicious patterns detected.
