Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad auto-invocation metadata, but no hidden code, data access, persistence, or destructive behavior was found.
Install only if you want a general workflow helper for skill-vetting or related reliability work. Be aware it may activate on broad terms unless your environment lets you restrict or disable implicit invocation.
The trigger phrases are broad enough to match common security, GitHub, or bug-fix requests that may not actually intend to invoke this skill. This can cause accidental activation, routing confusion, and unintended execution of a workflow in contexts where more specific or safer handling would be appropriate.
The manifest description says to use the skill whenever a user asks for broad terms like work-productivity, security, or needs almost any practical workflow, checklist, analysis, or implementation support. That activation scope is so ambiguous that it can match a wide range of unrelated requests, leading to accidental invocation and inappropriate delegation of sensitive security-adjacent tasks to a generic helper skill.
The trigger list is overly broad, especially terms like "security," "first," "before," and "github," which are common in ordinary conversations and unrelated tasks. This can cause the skill to activate unintentionally, potentially overriding more appropriate skills or injecting workflow guidance into unrelated contexts, reducing reliability and increasing the chance of unsafe or misleading assistance.
The trigger list includes very broad everyday terms such as "security", "first", "before", and "github", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that this skill intercepts requests outside its intended scope, leading to unintended guidance, workflow confusion, or unsafe substitution for more appropriate skills.
The trigger section uses a very broad natural-language starter phrase ('Help me ...') tied to a long requirement description, which can cause the skill to activate on ordinary user requests that were not intended to invoke this workflow. Over-broad activation increases the chance of misrouting prompts, unintended execution paths, and interference with more appropriate skills, especially in security-related contexts where precise routing matters.
The trigger phrases are broad enough to match ordinary requests about security, GitHub, bug fixing, or practical workflows, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad invocation increases the chance of unintended execution, context hijacking, and users receiving this skill's workflow when they did not explicitly request it.
This file is labeled as Chinese documentation but contains substantial English instructional content and trigger text, with no statement about language selection or user preference. That can violate language/locale policy expectations when a skill appears to force or assume a language without opt-in.
The skill description defines applicability very broadly, combining multiple generic domains and asking to use the skill whenever users need "practical workflow, artifact, checklist, analysis, or implementation support" for the requirement. This unclear boundary makes the router more likely to invoke the skill for loosely related tasks, which can reduce reliability and accidentally expose users to mismatched security or implementation advice.
The default prompt contains broad, common-language trigger terms such as 'help me' and generic work/security-related wording that can cause the skill to activate in situations far beyond a narrowly intended use case. Because this is a vetter/security-adjacent helper, unintended invocation could inject this skill into unrelated conversations, influencing outputs or exposing users to unnecessary prompt/context mixing.
Enabling implicit invocation without strong activation constraints allows the platform to auto-select this skill based on vague semantic matches rather than deliberate user choice. In a security/workflow helper, that increases the chance of accidental invocation in unrelated contexts, which can lead to overreach, confusion, and inappropriate handling of sensitive or security-relevant requests.
The invocation guidance uses a generic request form ('I need a practical workflow for ...') without clear boundaries on when this skill should or should not be selected. This can lead to unintended activation from loosely related productivity or implementation requests, causing incorrect tool selection and potentially exposing users to irrelevant or risky security-oriented outputs.
The file list explicitly defines English and Chinese instruction and guide files, but does not state that users may choose their preferred language or that language selection is optional. This can be read as a fixed locale arrangement rather than an opt-in language choice, which risks conflicting with language-choice policy expectations.
