Security audit
Security checks for vulnerabilities and agentic risk
The skill has no executable payload, but its localized instructions and implicit activation metadata are too broad and inconsistent for a security-gate skill.
Install only if you are comfortable with a security-review helper that may activate too broadly in some environments. The English workflow is reasonable, but the Chinese skill file and usage docs should be tightened before relying on it as a publication or activation gate.
The trigger phrases are broad, generic help requests that can match ordinary user intent unrelated to this security-review skill. That creates an invocation-confusion risk where the skill may activate unexpectedly, steering users into an unintended workflow and potentially affecting review or publication decisions without clear user consent.
The trigger phrases are extremely broad and include common words and generic help-seeking language, which can cause the skill to activate for ordinary unrelated requests. In a security-review skill, overbroad invocation is risky because it can unexpectedly steer conversations into this workflow, create prompt-routing confusion, and interfere with user intent or other skills.
Referenced artifact was not completely inspected
3. Review `SKILL.md` triggers for overbroad activation or misleading capability claims.
The manifest description does not match the skill’s declared purpose as a security review workflow helper and instead describes a broad demand-validation/productivity assistant. In a security-sensitive skill ecosystem, this mismatch can cause the wrong skill to be invoked, mislead users and reviewers about what the skill actually does, and weaken trust and review gates around activation or publication.
The description uses broad topical language to define when the skill should be used, rather than precise invocation criteria. This makes it easy for routing logic or users to apply the skill in contexts far beyond security review, increasing the risk of misclassification, unintended activation, and erosion of trust in security workflow tooling.
The body of the skill documentation repeatedly describes a generic workflow for fulfilling broad user needs instead of a focused security review process. This contradiction increases the chance that users or orchestration logic rely on the skill for security assurance when it may instead produce unrelated output, leading to ineffective review, accidental bypass of safety expectations, or publication of insufficiently vetted skills.
The trigger list contains extremely common words such as 'every', 'must', 'pass', and 'before', which can cause the skill to activate in many unrelated conversations. For a skill claiming to support security workflow decisions, accidental activation can inject irrelevant guidance, confuse users, and potentially interfere with more appropriate security controls or review flows.
The trigger sentence is extremely broad and reads like ordinary user language rather than a narrowly scoped activation condition. That increases the chance of unintended or opportunistic invocation, causing the security-review skill to activate in unrelated conversations and potentially steer workflows or collect context when the user did not explicitly request this skill.
This file is entirely presented in Chinese while also describing user-facing usage and trigger guidance, but it does not state that language is optional or user-selectable. That can constitute a locale or language policy issue if users are implicitly required to interact in a specific language without opt-in.
The file is explicitly a zh-CN localized skill and all instructions are presented in Simplified Chinese, but there is no natural-language indication that users may choose another language or opt in to this locale. That can violate language-choice policy when the skill is applied to users who did not request Chinese output.
The default prompt uses a generic activation description to 'scan this skill folder before activation or publishing' but does not define narrower trigger conditions, exclusions, or negative examples. In a manifest file, this can create ambiguity about when the skill should activate versus when a user is making a general request about reviewing a folder.
This trigger is ambiguous and insufficiently tied to the skill's stated function, so it may match requests that only vaguely mention a workflow or practical help. In a security workflow helper, ambiguous auto-invocation is risky because it can insert authoritative security guidance into the wrong context or activate tooling without clear user intent.
The file declares English and Chinese variants of the skill documentation, but it does not explain how the user's preferred language is selected or that language choice is optional. This can create a locale-policy concern if the skill defaults users into a language without explicit opt-in.