Security audit
Security checks for vulnerabilities and agentic risk
This is a small Markdown-only Chinese ETL helper skill with vague scheduling wording but no code, install hooks, persistence, credential use, or hidden behavior in the inspected artifacts.
Before installing, confirm whether Cron support means generating schedule expressions or actually creating scheduled jobs. The skill is not showing malicious behavior, but its documentation should better define activation, supported language, and scheduling boundaries.
The entire skill description and usage instructions are written only in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language or region-specific context. Under the policy, a forced language/locale without opt-in or documented justification is a natural-language policy violation.
The README makes a broad safety claim that the skill performs 'only text processing' and has 'no system command execution,' yet it also advertises Cron scheduling support. Scheduling jobs is an execution-capable feature and the mismatch can mislead reviewers or users about the skill's true operational capabilities and risk surface.
The trigger condition is extremely broad: any message containing the skill name or related instructions can activate the skill. In an agent environment, ambiguous activation increases the chance of unintended invocation, prompt-routing mistakes, or abuse through crafted user inputs that cause the pipeline tool to run when not explicitly requested. The reassuring safety statement elsewhere in the skill does not mitigate this and is itself mildly suspicious because it attempts to preempt security review.
The title, description, usage, and safety statements are entirely in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. This may violate language or locale policy when no user opt-in or documented regional constraint is provided.
No suspicious patterns detected.
