Security audit
Security checks for vulnerabilities and agentic risk
This skill is not overtly malicious, but it broadly orchestrates and dynamically loads other installed skills without clear enough consent, scoping, or capability limits.
Install only if you are comfortable with a meta-skill coordinating other installed skills. Prefer explicit slash triggers, review which subskills it will run, and confirm any action that can create reminders, modify state, use credentials, or call external services.
The skill documentation is written entirely in Chinese and includes Chinese-only trigger and usage text, but it does not state that the skill is intended only for Chinese-speaking users or provide an opt-in language choice. Under the language/locale policy, a skill should not implicitly force a specific language unless that constraint is clearly justified or optional.
SQP-3 applies to all file types and covers language or locale policy violations. The document is presented entirely in Chinese and names Chinese trigger phrases, but it does not state that users may choose another language or that the Chinese-only behavior is intentional and justified.
The skill markets itself as a collaboration engine, but its documented behavior includes creating reminders and executing other skills, both of which can affect system state or trigger privileged actions. Without clear disclosure and consent boundaries, users may unknowingly authorize side effects, especially when combined skills inherit broader capabilities than the top-level description suggests.
The skill explicitly describes loading arbitrary skill files by name, reading their content, and dynamically importing them for execution. That turns a 'combo/orchestration' feature into a generic code-loading mechanism, so any unsafe or malicious downstream skill can be invoked transitively, greatly expanding execution scope and bypassing the user's expectation of a simple coordination tool.
The manifest presents the display name, description, keywords, and categories primarily in Chinese, with no indication that users can choose another language or locale. This can constitute a language-policy issue when a skill implicitly assumes a specific language without documenting opt-in or regional restriction.
The trigger word set includes very generic phrases such as "多技能" and "技能组合", which are likely to appear in normal discussion unrelated to intentional skill invocation. In a meta-skill that coordinates multiple other skills, accidental activation is more dangerous than usual because it may broaden the scope of actions taken or cause unintended orchestration of other capabilities.
No suspicious patterns detected.
