Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording but no code, persistence, credential use, or hidden data handling.
Installers should be aware that this skill may activate too broadly for ordinary security, GitHub, or bug-fix requests. It is otherwise low risk as submitted because it is documentation-only and does not run code or request sensitive access.
The trigger phrases are generic help-seeking language and broad security-adjacent terms, which can cause the skill to activate in contexts the user did not explicitly intend. In an agent ecosystem, this creates prompt-routing ambiguity and increases the chance the skill intercepts unrelated requests, influencing security-sensitive workflows or analysis without clear user consent.
The trigger keywords are excessively broad, including generic terms like "security," "first," "before," and "github," which can cause the skill to activate in many unrelated conversations. In an agent environment, this increases the chance of unintended routing, context hijacking, or the skill influencing tasks it was not meant to handle, especially because the skill presents itself as a general workflow helper for security-adjacent work.
The trigger keywords are broad and generic, including terms like "security", "first", "before", "github", and "bug fix", which are common in ordinary user conversations. This can cause accidental invocation of the skill outside its intended scope, leading to inappropriate workflow steering, user confusion, and increased exposure to any unsafe behavior the skill may contain.
The trigger sentences and keywords use very broad, common terms such as 'security', 'first', 'github', and generic help phrasing, which can cause the skill to activate in many unrelated conversations. In an agent ecosystem, unintended activation can route user requests into the wrong workflow, leading to incorrect handling, prompt collisions, or accidental exposure of unrelated context to this skill.
The trigger phrases are broad, generic, and include common terms like "security," "first," "github," and "bug fix," which can cause the skill to activate outside its intended scope. In an agent ecosystem, unintended activation can route unrelated user requests into this workflow, increasing the chance of incorrect guidance, workflow confusion, or accidental invocation in sensitive contexts such as security review.
The description says to use the skill when a user asks for broad topics like "security" or needs almost any "workflow, artifact, checklist, analysis, or implementation support," which lacks clear boundaries for when the skill should or should not run. This ambiguity can lead to over-invocation and accidental handling of unrelated requests, making the skill more likely to interfere with safer or more appropriate routing decisions.
The activation description says to use the skill for broad categories like work-productivity, security, and practical workflow support, but it does not clearly delimit when this skill should be preferred over many other normal assistant behaviors. This ambiguity increases the chance of over-activation and misrouting, especially because the skill operates in a security-adjacent context where users may expect precise tool selection.
The default prompt is overly broad and uses generic trigger language that can cause the skill to be invoked in situations only loosely related to its intended purpose. In a security- and workflow-oriented skill, this increases the chance of accidental routing, over-collection of user context, or untrusted delegation into a skill that may influence sensitive analysis or remediation tasks.
Enabling implicit invocation without tight activation criteria allows the platform to auto-select this skill based on vague matches, which can lead to unintended invocation in unrelated or sensitive contexts. Because this skill presents itself as helping with security, vetting, and implementation support, accidental invocation could misdirect user workflows or expose the skill to security-relevant tasks without sufficient guardrails.
The file explicitly labels separate English and Chinese instruction files but does not state how the user's preferred language is selected. This can imply a locale/language handling policy that is predetermined rather than based on user choice.
This is a Chinese-language README file, but core descriptive content and all example trigger phrases are presented in English, which can effectively force a language preference without opt-in. The document does not state that users may interact in Chinese or choose their preferred language.
