Security audit
Security checks for vulnerabilities and agentic risk
The skill is not malicious, but its public purpose says comics while its instructions describe video/anime streaming features, so users should review the mismatch before installing.
Install only if you intended a Chinese-language anime/video streaming helper rather than a comics skill; the publisher should align the name, description, examples, and feature list before normal use.
The skill metadata claims a comics-reading/social/merch capability, but the body documents a different video/streaming product with playback, bitrate, and membership features. This mismatch can mislead users and downstream routing systems, causing the skill to be invoked in unintended contexts and potentially enabling deceptive capability substitution.
The heading and feature descriptions explicitly describe animation/video playback rather than a comics skill, directly contradicting the declared purpose of the agent skill. Such semantic inconsistency is dangerous because it obscures real behavior, weakens user consent, and increases the chance of improper invocation or trust abuse.
The example trigger phrases are highly generic and can match many ordinary user requests unrelated to this specific skill. Overbroad triggers increase the risk of accidental activation, routing confusion, and unintentional capture of user requests that should go to other skills or safer default handling.
All user-facing natural-language content in this skill is Chinese, and the file does not indicate that the skill is region-specific or that users may choose another language. Under the stated policy, forcing a specific language without opt-in can be a language/locale policy violation.
No suspicious patterns detected.
