Security audit
Security checks for vulnerabilities and agentic risk
This skill appears to be a broad, template-like CI/CD automation helper rather than malware, but it asks for command execution authority without clear operational limits.
Review this skill before installing. It does not show malicious code, persistence, or exfiltration, but it should only be used where you are comfortable granting an agent command execution for CI/CD or automation tasks. Confirm commands, credential use, and any deployment-affecting changes manually.
The manifest presents this as a CI/CD pipeline setup skill, but the body describes much broader generic automation, data analysis, and workflow orchestration. This scope mismatch can cause an agent or user to invoke the skill in unintended contexts and grant it more operational latitude than expected, especially given the declared exec capability.
The core-function section contradicts the stated CI/CD purpose by describing generic data processing, batch operations, and source validation rather than build/deploy pipeline changes. In a skill with read and exec tools, this ambiguity increases the chance of unsafe command execution or repository modifications outside the user's intended CI/CD scope.
The skill discusses deployment, command execution, files, and environment setup, but does not prominently warn users that it may execute commands or make deployment-affecting changes. In CI/CD contexts, hidden or under-disclosed exec behavior can directly affect build systems, secrets, artifacts, and production deployment paths.
The trigger condition says the skill activates whenever the user needs to perform 'related operations,' which is too vague for a skill capable of command execution. Overbroad triggering increases the risk of accidental invocation in inappropriate contexts, leading to unintended automation or changes in development environments.
The manifest text mixes Chinese and English in core user-facing description fields without stating whether the skill supports language selection. This can create an implicit language policy issue because the skill presentation assumes a specific locale rather than offering an opt-in or user preference.
No suspicious patterns detected.
